Violation

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 44

All topics

Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening
Oct 1, 2026Jie Tang, Chuanlong Xie, Lixing ZhuFairness Audits Algorithmic Fairness
School of Statistics, Beijing Normal University, Zhuhai, Guangdong 519087, China
Where Do Multi-Agent Systems Fail? Evidence-Grounded Diagnosis of Collective Mechanisms
Sep 30, 2026Zhengye HanDiagnosis Collective Behaviors
New York University New York, NY, USA
When Does Randomized Oversight Align AI Agents That Can Conceal?
Sep 29, 2026Joshua S. Gans, Richard HoldenModel Auditing Security Evaluation
UNSW Business School
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Sep 28, 2026Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev +1Modern Text-To-Image Models Violation
White Circle
AdaGuard: An Adaptive Guard Model with User-defined Policies
Sep 28, 2026Yunhao Feng, Yifan Ding, Yuxiang Xie +4Safety Claims Adversarial Evaluation
National University of Defense Technology · Fudan University
CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification
Sep 7, 2026Yali Du, Hui Sun, San-Zhuo Xi +1Image-To-Cad Generation Solidworks
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China
SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents
Sep 7, 2026Chenyu Zhou, Qiliang Jiang, Shuning Wu +1Admissibility Large Language Model Policy Optimization
School of Engineering, Institute of Science Tokyo, Japan · College of Control Science and Engineering, Zhejiang University, China · Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Exact Risk-Complexity Laws for Projective Boundaries in Scenario Optimization and Distribution-Free Certification
Sep 1, 2026Giuseppe C. CalafioreFinite-Sample Certificates Boundaries
Department of Electronics and Telecommunications, Politecnico di Torino, Italy
The Safeguard Worked. Is the LLM System Safer?
Sep 1, 2026Pingyu Wu, Weiming Zhang, Nenghai YuLarge Language Model Safety Safer
University of Science and Technology of China · 2Hefei AiDA Lab
DevIntent: How Much Does LLM-Generated Code Violate Developer Intent?
Aug 7, 2026Susana Haing, Natan Vidra, Spurthi SettyCode Quality Violation
Anote AI
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
Aug 5, 2026Zijie Zhuang, Changxin Lao, Pengbo Xu +13Evidence-Grounded Questions Category-Aware Atomic Claims
Kuaishou Technology, Beijing, China
Local Violation Certification for Linear Predict-Then-Optimize Pipelines
Aug 5, 2026Ş. İlker Birbil, Wenhao ChiViolation Conformal Risk Control
Faculty of Economics and Business, University of Amsterdam, The Netherlands · Yau Mathematical Sciences Center, Tsinghua University
Diagnosing Under-Development of Irreversible Processes in Video Generation
Aug 1, 2026Jian Xu, Yanning Wu, Delu Zeng +2Video Generation Irreversibility
Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
Jul 26, 2026Nikolaos Kekatos, Panagiotis Katsaros, Alexios Lekidis +2Runtime Enforcement Swarms
Clone Systems, Larnaca, Cyprus · Aristotle University of Thessaloniki, Thessaloniki, Greece · University of Thessaly, Larissa, Greece
DRC-Aid: Design-Rule Correction via Agentic Framework utilizing Inference-Time Large Language Models
Jul 23, 2026Anushka Mukherjee, Kang He, Kaushik RoyElectronic Design Automation Layouts
Purdue University West Lafayette, Indiana, USA
Learning to Detect UI Principle Violations via Reinforcement Learning
Jul 22, 2026Nishi Mehta, Swathi Alse, Himani Kumawat +2Code Quality Interaction Design
University of California, Santa Cruz · Carnegie Mellon University
Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning
Jul 21, 2026Timothy TomashevskiySafety Constraints Offline Reinforcement Learning
Department of Computing and Software McMaster University Hamilton, Ontario, Canada
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
Jul 15, 2026Mohammad Allahbakhsh, Mohammad Hassan Bahari, Moslem Attar-RaoufPenetration Testing Adversarial Evaluation
Computer Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran. · Sensifai BV, Brussels, Belgium.
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
Jul 8, 2026Yuan Chen, Zhenyu Hu, Mengge Xue +5Rectification Ads
Tencent
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
Jun 29, 2026Shuchang Ye, Jinqiang Yu, Zhujun Xiao +6Content Moderation Streaming Video
1TikTok
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
Jun 28, 2026Seongjae Kang, Taehyung Yu, Sung Ju HwangEnforcement Violation
KAIST
Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models
Jun 27, 2026Tassilo Klein, Johannes HoffartTabular Foundation Models Counter Turing Test
SAP SE
Beyond Accuracy: Measuring Logical Compliance of Predictive Models
Jun 18, 2026Guillaume Olivier Delplanque, Pierre Genevès, Nabil Layaïda +1Violation Logistic Regression
LIG · LIG,TYREX
Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates
Jun 16, 2026Meng Li, Xiaohua Yang, Jie Liu +1Machine Learning Surrogates Validation
School of Computing, University of South China, Hengyang, China · Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment, Hengyang, China · CNNC Key Laboratory on High Trusted Computing, Hengyang, China
GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking
Jun 14, 2026Aman Anifer, Vignesh Kumar Kembu, Vishnu M +4Large Language Model Jailbreaks Violation
Department of Computer Applications, Cochin University of Science and Technology, Kerala, India. · Department of Electrical, Computer and Biomedical Engineering, University of Pavia, A. Ferrata, 5, Pavia, 27100, Italy.
Constitutional Value Potentials: reading and steering internal priority margins in language models
Jun 13, 2026Tong Che, Rui WuHuman Values Value
Rutgers University
The Violation Situation Pattern: A Knowledge-Graph Pattern for Compliance Violations
Jun 2, 2026Nima Kamali Lassem, Fuqi Song, Seyid Amjad AliViolation Compliance
DiliTrust, Paris, France · Department of Information Systems and Technologies, Bilkent University, Türkiye
GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
May 27, 2026Ojas Nimase, Zhe Chen, Gengpei Qi +2Ranking Violation
University of Southern California · Arizona State University
When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
May 25, 2026Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2Interpretable Anomaly Detection Unsupervised Detection
School of Electrical Engineering and Robotics, Faculty of Engineering, −Queensland University of Technology, Brisbane, Queensland, Australia
FoodMonitor: Benchmarking MLLMs for Explainable Compliance Analysis
May 23, 2026Ruihao Xu, Xingming Shui, Jingxuan Niu +4Training-Free Video Anomaly Detection Compliance
Tsinghua Shenzhen International Graduate School, Tsinghua University
Passive Construction Site Safety Monitoring via Persona-Scaffolded Adversarial Chain-of-Thought VLM Verification
May 19, 2026Ananth Sriram, Neel Mokaria, Rajveer SinghVideo Surveillance Violation
Department of Computer Science, University of Maryland, College Park, MD, USA
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
May 19, 2026Ahmad Yehia, Abduallah Mohamed, Kun Qian +4Violation Cognitive Science
The University of Texas at Austin · Meta Reality Labs · University of Calgary
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
May 18, 2026Rohith UppalaAccess Control Model Context Protocol
Independent Researcher
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
May 16, 2026Zoher Kachwala, Bao Tran Truong, Rasika Muralidharan +3Content Moderation Internal Pluralism
Observatory on Social Media, Indiana University, USA · Center Synergy of Systems, TUD Dresden University of Technology, Germany
No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
May 13, 2026Ying Li, Hongbo Wen, Yanju Chen +3Fuzzing Violation
University of California, Los Angeles · University of California, Santa Barbara · University of California, San Diego
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
May 9, 2026Linfeng Fan, Yuan Tian, Ziwei Li +1Contracts Violation
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
Teaching LLMs Program Semantics via Symbolic Execution Traces
May 7, 2026Jonas Bayer, Stefan Zetzsche, Olivier Bouissou +3Formal Verification Traces
University of Cambridge · Amazon Web Services
SoK: Robustness in Large Language Models against Jailbreak Attacks
May 6, 2026Feiyue Xu, Hongsheng Hu, Chaoxiang He +9Large Language Model Jailbreaks Large Language Model Safety
Shanghai Jiao Tong University, China · Microsoft Corporation
MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
Apr 30, 2026Haonan Li, Tianjun Sun, Yongqing Wang +1Model Context Protocol Information-Flow Control
Key Laboratory of Intraplate Volcanoes and Earthquakes (China University of Geosciences, Beijing), Ministry of Education, Beijing 100083, China · School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China
Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems
Apr 24, 2026Jie Wu, Ming GongViolation
Atlassian
Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon
Apr 23, 2026Cooper VeitContracts Kernel Method
Ashiba Research
When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints
Apr 18, 2026Yuheng Chen, Zhiyu Wu, Bowen Cheng +2Large Language Model Safety Large Language Models Fail
Kagoshima University · Fudan University · China University of Petroleum-Beijing
SafeMath: Safe Solutions for Unsafe Math Word Problems
Mar 26, 2026Sagnik Basu, Subhrajit Mitra, Aman Juneja +3Large Language Model Safety Safety Alignment
1Indian Institute of Technology Kharagpur · 2Cisco Systems · 3National University of Singapore
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
Dec 3, 2025Oren Rachmil, Avishag Shapira, Roy Betser +5Large Language Model Policy Optimization Large Language Model Safety
Fujitsu Research of Europe · Ben-Gurion University of the Negev

Oct 1, 2026, stat.MLJ/K move · Enter open · S save

Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening

Jie Tang, Chuanlong Xie, Lixing Zhu

School of Statistics, Beijing Normal University, Zhuhai, Guangdong 519087, China

Fairness Audits Algorithmic Fairness Model Auditing Decision Thresholds Violation Screening

Open paper AskPDF arXiv

As artificial intelligence is increasingly deployed, algorithmic unfairness has raised growing concerns and intensified demands for transparent fairness auditing. In practice, the tolerable degree of algorithmic unfairness depends on the specific legal, ethical, or application context. Given a prespecified tolerance threshold, an important statistical question is how to determine whether a group disparity exceeds the allowable tolerance across different auditing objectives. To address this problem, we develop a unified tolerance-based fairness auditing framework for two complementary auditing objectives: violation certification, which prioritizes control of false violation declarations, and sensitivity screening, which prioritizes reducing missed violations. For the first objective, we develop a constrained empirical likelihood test for formal settings that uses least-favorable-point calibration and can be combined with false flagging rate control for simultaneous subgroup auditing. For the second objective, we develop split empirical likelihood and adjusted split empirical likelihood tests using an adaptive boundary-proxy principle for early-warning settings. Numerical experiments show the distinct error-control--sensitivity trade-offs of these procedures. A COMPAS analysis illustrates the framework in predictive fairness auditing.

Momentum

Related topics

Latest papers 44