Software Security

Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 61

All topics
CardsList

  1. Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair

    Oct 5, 2026Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2Agent Failure AnalysisAutomated Program Repair

    Tampere University, Tampere, Finland

  2. AuraForge: Scaling Security Supervision for Training Coding Agents

    Oct 1, 2026Danqing Wang, Songwen Zhao, Harsh Sharma +4AI Coding AgentsSoftware Security

    Carnegie Mellon University · University of California, Los Angeles · ScOp Venture Capital.

  3. API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary

    Sep 27, 2026Patrick Kenney, Hadi Ahmadi, Denis Lusson +2Software SecurityLLM Agent Security

    Corvic AI Research

  4. Evaluating Coding Agents on Kernel Exploit Generation

    Sep 22, 2026Junyoung Jang, Gwanhyun Lee, Hwiwon Lee +4AI Coding AgentsSoftware Security

    Independent Researcher · University of Illinois Urbana-Champaign · Ministry of National Defense, Republic of Korea

  5. SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses

    Sep 20, 2026Xingyu Li, Juefei Pu, Haonan Li +4Software Vulnerability DetectionLLM-Based Program Synthesis

    University of California, Riverside

  6. Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

    Sep 17, 2026Sarah Radway, Andrew Cheng, Vijay Janapa Reddi +1Language Model FingerprintingSoftware Security

    Harvard University

  7. 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 MeloSoftware Vulnerability DetectionSoftware Security

    Toronto Metropolitan University Toronto, Canada

  8. Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics

    Sep 8, 2026Leming Shen, Shikai Geng, Yuanqing Zheng +1CybersecuritySoftware Security

    University College London · The Hong Kong Polytechnic University

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

    Sep 7, 2026Jiahao Shi, Edward Tsien, Yifeng Di +10LLM Agent EvaluationSoftware Security

    Department of Computer Science, Purdue University · Red Hat

  10. CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

    Sep 2, 2026Varun Gadey, Ziad Marey, Alexandra DmitrienkoData Poisoning AttacksSoftware Security

    University of Duisburg-Essen, Germany

  11. Automated Vulnerability Injection in Smart Contracts Using Large Language Models

    Sep 2, 2026Luca Migliaccio, Roberto Natella, Naghmeh Ivaki +2Software SecuritySoftware Vulnerability Detection

    Universit`a degli Studi di Napoli Federico II · Gran Sasso Science Institute (GSSI) · University of Coimbra, CISUC/LASI, DEI +1

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

    Sep 1, 2026Phong Trinh Duy, Trang Dang Yen, Hung Nguyen-Huu +5Software SecurityKG Completion

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

  13. MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

    Aug 26, 2026Miseon Yu, Jaehoon Choi, Younghan Lee +1Code GenerationSecure Code Generation

    Seoul National University · Seoul, Republic of Korea · Sungshin Women’s University

  14. CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

    Aug 24, 2026Jian Yang, Haau-Sing Li, Shawn Guo +10CybersecuritySoftware Security

    Beihang University · ELLIS · IQuest Research +1

  15. Vulnerabilities, Secrets and Misconfiguration in the Highest-Exposure Docker Hub Images

    Aug 2, 2026Cristhian Kapelinski, Beatriz Machado, Diego KreutzSoftware Vulnerability DetectionCybersecurity

    *AI Horizon Labs, Federal University of Pampa (UNIPAMPA), Alegrete, Brazil

  16. An AI Approach to Verified Production Cryptographic Libraries

    Aug 2, 2026Chuyue Sun, Su Fong, Zhiyi Kuang +5Software SecurityProgram Synthesis

    Stanford University · &Truth · University of North Carolina at Chapel Hill +2

  17. EduPluginBench: Executable Assurance for AI-Generated Educational Plugins

    Aug 1, 2026Nizam KadirSoftware SecurityRuntime Assurance

    Singapore University of Technology and Design, Science, Mathematics and Technology, Singapore, Singapore

  18. Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale

    Jul 31, 2026Nicolás PadillaMCP SecuritySoftware Vulnerability Detection

    CobaltoSec

  19. Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?

    Jul 28, 2026Farooq ShaikhAutomated Program RepairLLM Prompting

    Dynatrace Research, Linz, Austria

  20. The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting

    Jul 26, 2026Ishpuneet Singh, Shreyas Mahajan, Gurjot Singh +1LLM PromptingCybersecurity

    Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, India · David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada

  21. Qubes OS Security in the Public Record

    Jul 16, 2026Alfonso De GregorioSoftware Vulnerability DetectionCybersecurity

    Pwnshow

  22. The Prover Is the Judge: Verified Security Software from AI Coding Agents in Ada/SPARK

    Jul 15, 2026Tobias PhilippAI Coding AgentsCode Generation

    secunet Security Networks AG, Essen, Germany

  23. Understanding the Impact of AI Code Assistants on Security API Usage: An Empirical Study

    Jul 13, 2026Zahra Mousavi, Chadni Islam, M. Ali Babar +2AI Coding AgentsSoftware Security

    Centre for Research on Engineering Software Technologies (CREST) & Adelaide University, Australia · 2Edith Cowan University, Australia · 3CSIRO’s Data61, Australia

  24. Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

    Jul 11, 2026Igor Santos-GrueiroSoftware SecurityLLM Agent Security

    International University of La Rioja

  25. Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code

    Jul 10, 2026Chunqiu Steven Xia, Courtney MillerSoftware EngineeringSoftware Engineering Agents

    University of Illinois Urbana-Champaign · Urbana, IL, USA · George Washington University +1

  26. The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

    Jul 7, 2026Mohammadreza RashidiAI Coding AgentsSoftware Security

    Department of Computer Science AI and Media Analysis Lab Berlin, Germany

  27. Advanced Topic Modeling Techniques for Categorizing Software Vulnerabilities

    Jul 4, 2026Utkarsh Tiwari, Spoorthi M, Anirudh S +1Software Vulnerability DetectionTopic Modeling

    Department of Computer Science & Engineering, Amrita School of Computing, Bengaluru, Amrita Vishwa Vidyapeetham, India

  28. Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

    Jul 2, 2026Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4Software Engineering AgentsCybersecurity

    National University of Singapore · Nanyang Technological University · The Hong Kong University of Science and Technology (Guangzhou)

  29. Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities

    Jun 25, 2026Corban Villa, Sohee Kim, Austin Chu +2Differential TestingSoftware Vulnerability Detection

    UC Berkeley

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

    Jun 24, 2026Jintao Huang, Fengqing Jiang, Radha Poovendran +1Automated Program RepairSoftware Vulnerability Detection

    1The Ohio State University · University of Washington