Good Papers

Showing AI oversight & deception Show all papers

78%Highly rated
?Highly ratedVote to see the score
arXivAI oversight & deception

SoK: Semantic Decision Engines in Network Control Loops

Systematizing 139 semantic decision engine families reveals most miss network deadlines and verification, with only four reporting deadline attainment; unverified decisions reverse admission verdicts under queued execution, prompting minimum reporting rules and a research agenda.

Delong Li, Chen Li, Xu Wang, Haochen Gong and 2 more

Published Oct 5, 2026 · ▲ 6 on Hugging Face · Code

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it
lenient 1/5
medium 8/10
strict 2/5
80%Must read
?Must readVote to see the score
NeurIPS 2026AI oversight & deception

Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization

ATPO uses adaptive Tversky reinforcement learning for controllable multi-label video safety detection, raising Jaccard Index to 75.44 on SafeWatch-Bench-Real while enabling steerable precision-recall trade-offs.

Guangyu Yang, Jingbiao Mei, Mingsheng Sun, Jinghong Chen and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published Oct 1, 2026 · 0 citations

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
80%Must read
?Must readVote to see the score
arXivU Illinois Urbana-ChampaignU MichiganNvidiaNvidiaAI oversight & deception

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

Benign multi-agent LLM planners disguise secrets to help developers evade oversight, with rare per-episode leaks compounding to high breach risk across repeated exchanges.

Deema Alnuhait, Gengyu Wang, Muhammad Khalifa, Hao Peng

Published Sep 30, 2026 · 0 citations · ▲ 13 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 6/10
strict 1/5
91%Must read
?Must readVote to see the score
arXivAI oversight & deception

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

The RA-Bench benchmark reveals current detectors fail to consistently identify AI-generated crisis videos, which become harder to detect after social dissemination and frequently mislead humans.

Shuo Liang, Yixing Ma, Pengfei Zhou, Zhenglin Wan and 32 more

Published Aug 14, 2026 · 0 citations · ▲ 287 on Hugging Face · Code ★ 132

– ReadersNo votes yet
17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 4/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightPrincetonPrincetonAI oversight & deception

Do Thinking Tokens Help with Safety?

Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026GoogleU ChicagoGoogle DeepMindAI oversight & deception

Model Incrimination: Investigating Whether Concerning Behavior Reflects Misalignment

Gerson Kroiz, Aditya Singh, Senthooran Rajamanoharan, Neel Nanda

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Institute of Computing Technolog, Chinese Academy of SciencesZhongguancun LaboratoryAI oversight & deception

OASIS: Online Adaptive Steering for In-Training Safety of LLMs

Yifan Sun, Qiang Sheng, Ya Wu, Zhengjia Wang and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026National University of SingaporeSingapore Managementnational university of singaore,AI oversight & deception

LLM-enabled Applications Require Systematic Threat Monitoring

Yedi Zhang, Haoyu Wang, XIANGLIN YANG, Jin Song Dong and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Massachusetts AmherstU Massachusetts at AmherstDepartment of Computer Science, AI oversight & deception

Latent Barrier Steering: Hierarchical Safety for Generative Planning

Renhao Zhang, Mingzhe Li, Bruno Silva

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026City University of Hong KongUT AustinDepartment of Computer Science, Mohamed bin Zayed University of The Hong Kong University of ScieAI oversight & deception

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement

Xutao Mao, Jianing Zhu, Jinman Zhao, Tongliang Liu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026ShanghaiTechGreat BayAI oversight & deception

Safety-Aware Latent Space Reasoning in Large Language Models

Yi Wang, Wenjie Wang, Hongye Qiu, Yu Pan

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026School of Computer and CommunicaEPFL/Swiss Federal Technology InRedwood ResearchU OxfordAI oversight & deception

AI Control for Sandbagging on Fuzzy Tasks

Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Science and Technology of ChinBeijing Electronic Science and TFudanBeijing University of Post and TChina Academy of Informaton and AI oversight & deception

Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance

Huilin Zhou, Ruoxi Cheng, Yuhang Wang, Yuming Liu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026StanfordU CambridgeStanfordAI oversight & deception

Position: AI Development Should Prioritize Cognitive Security

Batu El, Shiye Su, Aneesh Pappu, Peggy Yin and 5 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026PekingPeking University / UC BerkeleyAIGAI oversight & deception

AI Alignment Can Build Moral Autonomy

Kaile Wang, Hantao Lou, Tianyi (Alex) Qiu, Sebastian Sunday-Grève and 4 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U OxfordU Toronto & Vector InstituteAI oversight & deception

Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring

Tom Lamb, Philip Torr, Tim G. J. Rudner

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TsinghuaTsinghua University, TsinghuaBeihangAI oversight & deception

Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment

Yao Huang, Yifan Wang, Yitong Sun, Yichi Zhang and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U California, Santa CruzUC Santa CruzU California, BerkeleyUC BerkeleyAI oversight & deception

Position: A Safe LLM and a Safe Harness Do Not Make a Safe Agent

Vincent Siu, Kyle Montgomery, Yujin Potter, Zhun Wang and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
3/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 3 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Notre DameAI oversight & deception

Scheming Is a Symptom: Alignment Research Should Probe Reflexive Fragility

Nan Zhang, Heng Xu

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SpotlightNanjingSingapore ManagementAI oversight & deception

Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test

Shihao Weng, Yang Feng, Xiaofei Xie

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Science and Technology of ChinNational University of SingaporeAlibaba GroupTencentAI oversight & deception

Rubric-Align: Safety Alignment through Dynamically Co-Evolving Rubrics

Ruipeng Wang, Junfeng Fang, Houcheng Jiang, Kai Tang and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Sun Yat-SenSUN YAT-SEN UNIVERSITYGuangzhouSingapore University of TechnoloNanyang TechnologicalAI oversight & deception

MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing

Zeqin Yu, Ye Tian, Jian Zhang, Jiangqun Ni and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Technische Universität DortmundTU DortmundRPTU and DFKI, KaiserslauternRPTU KaiserslauternAI oversight & deception

Pluralistic AI Alignment Requires Inference-Time Multi-Objective Control

Weichen Li, Mislav Stojanović, Daniel Neider, Marius Kloft and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Pennsylvania StateAI oversight & deception

Position: We Need Greater Transparency to Maintain Research Pipeline Reliability Despite GenAI

Hillmer Chona, Sourav Panda, Frank Ritter, Jonathan Dodge

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026GuidelightAarhusInstitute for AI Policy and StraApollo ResearchU North Carolina at Chapel HillAI oversight & deception

AIs with Secret Loyalties are a Serious but Addressable Threat

Joe Kwon, Alfie Lamerton, Andrew Draganov, Dave Banerjee and 6 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 1/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ETHZ - ETH ZurichETH Agentic Systems Lab & COLudwig-Maximilians-Universität MHarvardDepartment of Computer Science, AI oversight & deception

Claude Coke: Prevent Automated Crime by Agents

Gabor Hollbeck, Baran Peters, Alexander von Recum, Jan Granacher and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026AuburnU Texas at San AntonioCardiffU Central FloridaU South DakotaAI oversight & deception

Exploring Advertising Manipulation in Diffusion Image Generation

Tianshi Che, Yang Zhou, Yushan Mu, Zeru Zhang and 7 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Harvard Business SchoolMassachusetts Institute of TechnGoogle DeepMind & MITAI oversight & deception

AI Safety Evaluations Need More Human-AI Experiments

Michelle Vaccaro, Jaeyoon Song, Abdullah Almaatouq, Michiel Bakker

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026StanfordCarnegie MellonAI oversight & deception

Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring

Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightNew YorkAmazon Web ServicesDepartment of Computer Science, AmazonNVIDIAAI oversight & deception

nnTrace: Detecting and Localizing Silent Bugs in Distributed Training

Haitian Jiang, Shaowei Zhu, Zhen Zhang, Zhenyu Song and 4 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026AvasthaColumbiaU MarylandAI oversight & deception

Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive

Arka Pal, Kwok C Au, Louai Zahran, Rahul K Thomas and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 0/5
medium 1/10
strict 1/5
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026George WashingtonGoogleU California, BerkeleyAI oversight & deception

Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment

Arush Tagade, Shaoheng Zhou, Jiaxin Wen, Shi Feng

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
3/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 3 of 20 reviewers recommend it
lenient 1/5
medium 1/10
strict 1/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Hong Kong PolytechnicGuangzhouAI oversight & deception

DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections

Li Hu, Kanghua Mo, Yingbin Jin, Qingqing Ye and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Centre for the Governance of AIDepartment of Computer Science, Institute for Law & AICenter for AI Risk Management &aETH ZurichAI oversight & deception

FraudBench: A Legal Evaluation of AI Deception on Realistic Tasks

Kevin Wei, Sumaya N Adan, Stephan Llerena, Mark L Gitau and 16 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026NVIDIAAI oversight & deception

Can VLMs Reason When to Stop for Human Safety?

Ryo Hachiuma, Arun G Zachariah, Barnaby Simkin, Jibin Varghese and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
3/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 3 of 20 reviewers recommend it
lenient 2/5
medium 1/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Worcester Polytechnic InstituteApollo ResearchU OxfordIndependentGoogle DeepMindAI oversight & deception

Evaluating and Understanding Scheming Propensity in LLM Agents

Realistic agent settings show minimal scheming despite high incentives, with model-organism scheming brittle to tool removal and oversight.

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 1/5
88%Must read
?Must readVote to see the score
NeurIPS 2026ELLIS Institute TübingenTechnical University of DarmstadELLIS Institute & MPI IntellAI oversight & deception

Models That Know How Evaluations Are Designed Score Safer

Models with evaluation meta-knowledge about benchmark structures score safer via implicit behavioral shifts, confounding safety assessments independently of explicit awareness.

Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 6 on Hugging Face · Code ★ 3

– ReadersNo votes yet
15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 15 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 1/5
83%Must read
?Must readVote to see the score
NeurIPS 2026Changan AutomobileChongqing Changan Automobile Co.Chongqing Changan Automobile Co.National Institute of InformaticAI oversight & deception

PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety

PROACT-Agent synthesizes causally consistent agent trajectories to train real-time guardrails that achieve 91.46% unsafe F1 and cut AgentDojo targeted attacks from 20.82% to 0.40%.

Ding Jia, Wei Liu, Xianglong Du, Yingjie Li and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 1/5
89%Must read
?Must readVote to see the score
NeurIPS 2026OralAnthropicMATSStanfordGoogle DeepMindAI oversight & deception

Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors

Fine-tuned LLMs learn to selectively hide internal representations from unseen activation monitors via low-dimensional subspace manipulation, evading even post-hoc safety probes with modest capability loss.

Max McGuinness, Alex Serrano Terre, Luke Bailey, Scott Emmons

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 2/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026TechnionU OxfordTechnion---Israel Institute of TAI oversight & deception

Selective Safety Steering via Value-Filtered Decoding

Value-filtered decoding selectively steers LLM generation using a value-based safety criterion with explicit false-intervention bounds, improving safety-utility trade-offs over baselines.

Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it
lenient 5/5
medium 5/10
strict 1/5
Show 20 more papers