Latest Research in Adversarial Robustness in Machine Learning

Top Research Topics in Adversarial Robustness in Machine Learning

• Cryptography and Security — 41 papers
• Software Engineering — 12 papers
• Artificial Intelligence — 10 papers
• Adversarial Robustness in Machine Learning — 7 papers
• Advanced Malware Detection Techniques — 5 papers
• Software Engineering Research — 4 papers
• Computation and Language — 3 papers
• Security and Verification in Computing — 3 papers
• Software System Performance and Reliability — 2 papers
• Machine Learning — 1 papers

Highest-Cited Papers

1. Detecting Adversarial Perturbations in AI-Generated Code: A Three-Tier Detectability Hierarchy (2 citations)
2. SPDZCoder: Combining Expert Knowledge with LLMs for Generating Privacy-Computing Code
3. RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
4. Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation
5. Mind the Gap: How SBOM Specification Ambiguities Lead to Divergent Software Bills of Materials. An Empirical Tool Study
6. Local Sparsity Enables Unsupervised LLM Safety Detection
7. Open or Frontier? A Cost- and Energy-Aware Benchmark of Large Language Models for Software Vulnerability Detection
8. AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination
9. Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
10. Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
11. ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
12. "Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation
13. A Memorization Floor for LLM Refinement of Decompiled Code
14. κ-Identity: Behavioral Fingerprinting for Continuous Verification of LLM Agents
15. Hunk-Constrained DPO: Segment-Level Optimization for Secure and Correct LLM Code Generation
16. CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
17. Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
18. Evaluating the Impact of Personalization in Conversational Cybersecurity Assistants
19. Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities
20. PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift