Exploitation

Follow this topic Ask about this topic

Recent momentum

-56%

4 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Exploitation.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Exploitation.

83 papers

Latest in Exploitation

Open your feed →

Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
Sep 12, 2026Jessica Pourleyli, Maitreyee Das Urmi, Glaucia MeloVulnerability Detection & Repair Code Quality
VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities
Sep 7, 2026Jiahao Shi, Edward Tsien, Yifeng Di +10Vulnerability Detection & Repair Exploitation
Harness-agnostic detection and immunization of reward hacking in self-evolving language models
Sep 7, 2026Rongxin Yang, Yang Liu, Shang Luo +10Exploitation
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
Aug 31, 2026Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs +3Agentic Benchmarks Exploitation
LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles
Aug 13, 2026Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1Vulnerability Detection & Repair Autonomous Driving
Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes
Aug 11, 2026Chen Xu, Zitian Guo, Chenyan XiongCitations Exploitation
Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify
Aug 8, 2026Ibne Farabi Shihab, Fariya AfrinProcess Reward Modeling External Reward Models
SafeDivertor: Faithful Divertor Heat Flux Reconstruction from Macroscopic Plasma State Signals via Time-Frequency Prior Exploitation
Aug 6, 2026Hao Si, Zehua Chen, Qingquan Yang +8Plasma Shape Control Heat Diffusion
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
Aug 6, 2026Yuru Feng, Yaoqi Chen, Beidi Zhao +7Skill Evolution Agent Skill Libraries
MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models
Aug 4, 2026Yu Ran, Wentao Zhao, Xin Zhang +1Black-Box Adversarial Attacks Graphical User Interface
Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
Jul 30, 2026Boning Li, Longbo HuangExploitation Exploration-Exploitation Dilemma
The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play
Jul 28, 2026Michael Macaulay, Harmony Bouabid, Guo Gen Ang +1Large Language Model Safety Cybersecurity
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
Jul 24, 2026Jiaqi Shao, Hanck Chen, Wei Zhang +2Agentic Benchmarks Exploitation
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Jul 15, 2026Rui Wang, Hongru Wang, Yi Chen +4On-Policy Distillation Teacher-Student Model Pairs
Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation
Jul 13, 2026Praneeth Narisetty, Shiva Nagendra Babu KoreExploitation Self-Evolving Agents
Multimodal Reward Hacking in Reinforcement Learning
Jul 10, 2026Jiayu Yao, Yiwei Wang, Anmeng Zhang +5Exploitation
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
Jul 8, 2026Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin +5Exploitation Safe Reinforcement Learning
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
Jul 6, 2026Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2Game-Theoretic Framework Imperfect-Information Games
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
Jul 4, 2026Weiyang Guo, Zesheng Shi, Longhui Zhang +3Agentic Reinforcement Learning Self-Improving Agents
Safety Targeted Embedding Exploit via Refinement
Jul 2, 2026Joshua Adrian CahyonoMultilingual Safety Large Language Model Safety
Projected Exploitability Descent for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games
Jun 28, 2026Sam GanzfriedNash Equilibria Imperfect-Information Games
Mitigating LLM-based p-Hacking by Preregistering for the Next LLM
Jun 26, 2026Maria Thomas, Kristina Gligoric, Nihar B. ShahLarge Language Mitigation
A multi-task spatiotemporal deep neural network for predicting penetration depth and morphology in laser welding
Jun 24, 2026Sen Li, Haichao Cui, Chendong Shao +2Laser Welding Camera
RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments
Jun 24, 2026Babak Rahmani, Sebastian Dziadzio, Joschka Strüber +2Reverse Engineering Agentic Benchmarks
CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?
Jun 24, 2026Jintao Huang, Fengqing Jiang, Radha Poovendran +1Smart Contracts Vulnerability Detection & Repair
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
Jun 24, 2026Liwei Yu, Shuo Li, Ming Zhou +2Penetration Testing Vulnerability Detection & Repair
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
Jun 17, 2026Gabriele Digregorio, Marco Di Gennaro, Francesco Pastore +3Vulnerability Detection & Repair Machine Learning
Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework
Jun 16, 2026Petar Radanliev, Omar Santos, Carsten Maple +1Security Analysis Runtime Enforcement
Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds
Jun 13, 2026Ömer Veysel Çağatan, Xuandong ZhaoArtificial Intelligence Safety Large Language Model Safety
Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning
Jun 13, 2026Yiwei Chen, Lichi Li, Kai Cheung +2Vulnerability Detection & Repair Exploitation
Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
Jun 11, 2026Tingqiang Xu, Hangrui Zhou, Tianle Cai +2Fairjudge Models AI Code Generation
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
Jun 10, 2026Frank Xiao, Mary PhuongSafe Reinforcement Learning Exploitation
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Jun 8, 2026Mohammad Beigi, Ming Jin, Lifu HuangExploitation Safe Reinforcement Learning
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Jun 8, 2026Ziqian Zhong, Ivgeni Segal, Ivan Bercovich +3Exploitation Agentic Benchmarks
Cheap Reward Hacking Detection
Jun 8, 2026Iván Belenky, Joaquín Itria, Steven JohnsExploitation Encoding Models
VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation
Jun 6, 2026Harshil Patel, Kunal PaiInjection Attacks Vulnerability Detection & Repair
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Jun 5, 2026Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori +3Coding Agents Clickbait Detection
Learning to Contest: Decentralized Robust Fairness in Cooperative MARL via Cross-Attention
Jun 4, 2026Can SavcıMulti-Agent Reinforcement Learning Adversaries
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Jun 3, 2026Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3Rubric-Based Reinforcement Learning Exploitation
Large Language Models Hack Rewards, and Society
Jun 2, 2026Wei Liu, Xinyi Mou, Hanqi Yan +2Large Language Model Safety Exploitation
FORGE: Multi-Agent Graduated Exploitation and Detection Engineering
Jun 2, 2026Farooq ShaikhVulnerability Detection & Repair Exploitation
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
Jun 1, 2026Pu Wang, Yao-Xiang DingBandits Sublinear Regret
Medication-Aware Financial Exploitation Detection for Alzheimer's Patients Using Edge-Aware Interaction Risk Modeling
May 30, 2026Farzana Akter, Lisan Al Amin, Rakib Hossain +2Alzheimer Medication Recommendation Framework
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
May 30, 2026Su Wang, Pin Qian, Yihang Chen +6Agent Skill Libraries AI Risk Assessment
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
May 27, 2026Geoffrey Bradway, Roger Creus Castanyer, Lorenz Wolf +3Exploitation Robotwin
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
May 24, 2026Wenlong Deng, Jiaji Huang, Kaan Ozkara +4Exploitation Low-Dimensional Structure
Real-Time Auto-Optimization in Unknown Environments via Structure-Exploiting Dual Control for Exploration and Exploitation
May 21, 2026Shiying Dong, Haoyang Yang, Qiwei Liu +1Optimal Control Exploration-Exploitation Dilemma
Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
May 20, 2026Amit Roth, Ankur Samanta, Matan Halevy +2Exploitation Artificial Intelligence Systems
Hallucination as Exploit: Evidence-Carrying Multimodal Agents
May 18, 2026Guijia Zhang, Hao Zheng, Harry YangMultimodal Agents Certificates
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
May 17, 2026Zehan Sun, Dingfan Chen, Songze LiLanguage Model Evasion Attacks Exploitation
Imperfect World Models are Exploitable
May 15, 2026Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel +2Exploitation World Models
Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
May 14, 2026Juho Kim, Fei Fang, Tuomas SandholmWatermarks Imperfect-Information Games
ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
May 13, 2026Seunghyun Lee, David BrumleyExploitation Vulnerable Code
Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing
May 13, 2026Daniel Fernández-González, Cristina Outeiriño CidSequence-To-Sequence Models Transformer Encoder
Decaf: Improving Neural Decompilation with Automatic Feedback and Search
May 12, 2026Alexander Shypula, Osbert Bastani, Edward SchwartzDisassembly Reverse Engineering
Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
May 11, 2026Neil Fendley, Zhengyu Liu, Aonan Guan +2Agentic Workflows Hijacking
ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
May 11, 2026Zhun Wang, Nico Schiller, Hongwei Li +13Vulnerability Detection & Repair Exploitation
Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust
May 11, 2026Shijun Lei, Quang Nguyen, Swapneel S Mehta +7Multi-Agent Simulations Agentic Commerce
Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models
May 10, 2026Cameron Berg, Roshni LullaDeception Large Language Model Bias
Position: AI Security Policy Should Target Systems, Not Models
May 10, 2026Michael A. Riegler, Inga StrümkeVulnerability Detection & Repair Artificial Intelligence Risk

Sep 12, 2026 · cs.CRJ/K move · Enter open · S save

Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code

Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo

Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted as a scalable, reproducible, and inexpensive security gate, but cannot directly observe runtime exploit behaviour. Vulnerabilities dependent on adversarial inputs, execution context, or exploit chaining may evade static checks while remaining exploitable in practice, yet passing static analysis is often treated as evidence of secure behaviour. This paper introduces the Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers. We evaluate 1,355 Python samples from SecurityEval, RedCode, and CyberNative datasets. Of the 654 samples producing no findings under the composite Bandit-Semgrep gate, the LLM detection stage identified 394 candidate vulnerabilities across 235 files. Dynamic verification confirmed or partially confirmed exploitability in 95 files, yielding an inclusive pipeline rate of 14.53% (roughly 1 in 7 statically clean samples). This rate represents the proportion of Bandit-Semgrep-clean samples for which the pipeline identified a candidate vulnerability and obtained runtime evidence supporting exploitability. Outcomes varied by dataset: among candidate file--CWE pairs, confirmed exploitability was 33.7% for RedCode, 28.6% for CyberNative, and 5.4% for SecurityEval. Several frequently confirmed classes, including CWE-338 and CWE-916, were flagged by neither Bandit nor Semgrep. These findings indicate that static-analysis success and runtime security are hierarchical layers of software assurance rather than interchangeable measures, and have the potential to reshape how AI-generated and security-sensitive code is evaluated.

Vulnerability Detection & Repair Code Quality Exploitation

Open paper Ask about it PDF