Model Vulnerabilities

Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 39

All topics
CardsList

  1. Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks

    Oct 5, 2026Tobias Heldt, Matt Turk, Christoph Landolt +1Model Vulnerabilities

    XOR · Protege · CISPA Helmholtz Center for Information Security

  2. Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection

    Sep 29, 2026Sabrina Kaniewski, Tim Krämer, Julius Bächle +3Model VulnerabilitiesSoftware

    Institute for Secure Networked Systems, Esslingen University, Germany · Esslingen University, Germany · Institute for Intelligent Systems, Esslingen University, Germany +1

  3. Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery

    Sep 28, 2026Kaikai Zhang, Zihan Zhang, Yuchong Xie +4Model VulnerabilitiesHypothesis

    The Hong Kong University of Science and Technology

  4. Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale

    Sep 14, 2026Aman Priyanshu, Supriti Vijay, Kimia Majd +8Model VulnerabilitiesVulnerable Code

    1Foundation AI–Cisco Systems Inc. · 3Carnegie Mellon University · †Work done while at Foundation AI +1

  5. No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

    Sep 9, 2026Zehua Zhang, Jie Hu, Pratham Hegde +13Common Vulnerabilities And ExposureModel Vulnerabilities

    School of Computing and Augmented Intelligence, Arizona State University

  6. VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

    Sep 7, 2026Jiahao Shi, Edward Tsien, Yifeng Di +10Model VulnerabilitiesExploitation

    Department of Computer Science, Purdue University · Red Hat

  7. Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion

    Sep 1, 2026Phong Trinh Duy, Trang Dang Yen, Hung Nguyen-Huu +5Model VulnerabilitiesCommon Vulnerabilities And Exposure

    Hanoi University of Science and Technology, Vietnam · The University of Sydney, Australia · Singapore Management University, Singapore +3

  8. EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming

    Aug 3, 2026Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne +4Model VulnerabilitiesGraph Representations

    Syracuse University · HRL Laboratories

  9. Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

    Jul 28, 2026Abu Bakar SiddikCybersecurityModel Vulnerabilities

    Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh

  10. Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs

    Jul 20, 2026Sam Relins, Daniel BirksPolicingModel Vulnerabilities

    School of Law, University of Leeds, Leeds, UK

  11. Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

    Jul 7, 2026Mingchen Li, Meikang Qiu, Zifan Peng +4Large Language Model SafetyModel Vulnerabilities

    University of North Texas, USA · Augusta University, USA · Newcastle University, United Kingdom

  12. JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode

    Jul 2, 2026Norbert Sandor Szolnoki, Gabor AntalModel VulnerabilitiesLeakage

    University Of Szeged Szeged, Hungary

  13. A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

    Jun 30, 2026Seyed Bagher Hashemi Natanzi, Bo TangLarge Language Model SafetyModel Vulnerabilities

    Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA

  14. CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?

    Jun 24, 2026Jintao Huang, Fengqing Jiang, Radha Poovendran +1Smart ContractsModel Vulnerabilities

    1The Ohio State University · University of Washington

  15. Evaluating LLMs for Real-World Web Vulnerability Detection

    Jun 19, 2026Sebastian Neef, Luca Jungnickel, Antonio Benjamin Buchholz +2Model VulnerabilitiesAttacker Large Language Model

    Technische Universität Berlin, Einsteinufer 17, 10587 Berlin, Germany · Freie Universität Berlin, Kaiserswerther Str. 16-18, 14195 Berlin, Germany

  16. Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

    Jun 18, 2026Arastoo Zibaeirad, Marco VieiraModel VulnerabilitiesLarge Language Model Safety

    University of North Carolina at Charlotte, Charlotte, NC, USA

  17. Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

    Jun 13, 2026Yiwei Chen, Lichi Li, Kai Cheung +2Model VulnerabilitiesExploitation

    Cisco Systems, Inc., San Francisco, CA, USA · Michigan State University, East Lansing, MI, USA

  18. FORGE: Multi-Agent Graduated Exploitation and Detection Engineering

    Jun 2, 2026Farooq ShaikhCommon Vulnerabilities And ExposureModel Vulnerabilities

    Dynatrace, Vienna, Austria

  19. Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research

    May 31, 2026Michael J. BommaritoModel VulnerabilitiesHypothesis

  20. SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

    May 26, 2026Hwiwon Lee, Jiawei Liu, Dongjun Kim +3Model VulnerabilitiesSecurity Evaluation

    University of Illinois Urbana-Champaign

  21. Demystifying the Mythos or Disrupting Bugonomics? From Zero-Day Asymmetry to Defender Remediation Throughput

    May 23, 2026Alfredo Pesoli, Herman Errico, Lorenzo CavallaroModel VulnerabilitiesRemediation

    Bynario · Vanta · University College London / Bynario

  22. PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection

    May 22, 2026Steffen J. Camarato, Yahya Hmaiti, Mandana Ghadamian +1Model VulnerabilitiesCommon Vulnerabilities And Exposure

    University of Central Florida Orlando, Florida, USA

  23. Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

    May 22, 2026Vivek Dahiya, Sunny Nehra, Vipul Dholariya +2Model VulnerabilitiesPenetration Testing

  24. Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

    May 14, 2026William Lugoloobi, Samuelle Marro, Jabez Magomere +2Attacker Large Language ModelFingerprint

    Oxford Internet Institute, University of Oxford · Department of Engineering Science, University of Oxford

  25. Quantifying Cyber-Vulnerability in Power Electronics Systems via an Impedance-Based Attack Reachable Domain

    May 14, 2026Hongwei Zhen, Ze Yu, Xin Xiang +2Cyber-Physical SystemPower Systems

  26. DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

    May 10, 2026Wenxin Tang, Wenbin Li, Junliang Liu +10Model VulnerabilitiesWhite-Box Spectral-Subspace-Guided Attack

    Tsinghua University · Hunan University · Dalian Maritime University +9

  27. Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches

    May 7, 2026Isaac David, Arthur GervaisModel VulnerabilitiesReverse Engineering

    University College London

  28. Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts

    May 5, 2026Xing Zhang, Keyu Zhang, Taohong Zhu +1Smart ContractsModel Vulnerabilities

    NetX Foundation Zug, Switzerland · Department of Computer Science University of Oxford Oxford, UK · Department of Computer Science The University of Manchester Manchester, UK

  29. When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI

    May 1, 2026Alfredo Madrid-García, Miguel RujasChatbotsPrivacy

    Escuela Técnica Superior de Ingenieros de Telecomunicación Universidad Politécnica de Madrid Avenida Complutense, 30, Madrid, 28040, Spain

  30. Tatemae: Detecting Alignment Faking via Tool Selection in LLMs

    Apr 29, 2026Matteo Leonesi, Francesco Belardinelli, Flavio Corradini +1DeceptionModel Vulnerabilities

    Department of Computing Imperial College London

  31. A systematic literature Review for Transformer-based Software Vulnerability detection

    Apr 27, 2026Fiza Naseer, Javed Ali Khan, Muhammad Yaqoob +2Model VulnerabilitiesSystematic Review

  32. Jailbreaking Frontier Foundation Models Through Intention Deception

    Apr 27, 2026Xinhe Wang, Katia Sycara, Yaqi XieLarge Language Model JailbreaksJailbreak Attacks

    Carnegie Mellon University

  33. Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

    Apr 22, 2026Ronghao Ni, Mihai Christodorescu, Limin JiaModel Vulnerabilities

    Carnegie Mellon University · Google

  34. An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models

    Apr 20, 2026Hanrui Luo, Shreyank N GowdaLarge Language Model JailbreaksJailbreak Attacks

    School of Computer Science, University of Nottingham, Nottingham, United Kingdom.

  35. Surgical Repair of Insecure Code Generation in LLMs

    Apr 17, 2026Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth GargVulnerable CodeModel Vulnerabilities

    Tandon School of Engineering New York University · XBOW

  36. From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection

    Dec 11, 2025Chaomeng Lu, Bert LagaisseModel VulnerabilitiesBenchmark Datasets

    DistriNet Group-T, KU Leuven · Leuven, Belgium

  37. SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

    Oct 17, 2025Hanbin Hong, Shuang Wu, Shuya Feng +6Large Language Model SafetyLarge Language Model Evaluation

    University of Connecticut · University of Alabama at Birmingham · Independent

  38. On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification

    Jun 14, 2025Matteo Vilucchio, Lenka Zdeborová, Bruno LoureiroEmpirical Risk MinimizationModel Vulnerabilities

    Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL) · Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL) · Département d’Informatique, École Normale Supérieure - PSL & CNRS, France

  39. Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking

    Jul 2, 2024Jiexin Wang, Liuwen Cao, Xitong Luo +6Code GenerationVulnerable Code

    South China University of Technology, Guangzhou, China · University of Innsbruck, Innsbruck, Austria