ML Security Papers

LS01

Vulnerability Discovery

LLM-driven bug finding in source code, binaries, or systems

10 papers Browse all papers

Monthly publications

Paper types

attack 5

defense 2

tool 1

survey 1

benchmark 1

Domains

nlp 9

multimodal 1

Co-occurring categories

Other OWASP categories that appear on the same papers

LLM01 Prompt Injection

LS10 Benchmarks & Evaluation

LS06 Red-Team Agents

ML01 Input Manipulation Attack

LLM07 Insecure Plugin Design

LLM08 Excessive Agency

LS07 Blue-Team Agents

ML04 Membership Inference Attack

ML09 Output Integrity Attack

LS04 Patch & Remediation

Top cited papers

Takedown: How It's Done in Modern Coding Agent Exploits

SoK: Understanding (New) Security Issues Across AI4Code Use Cases

Semantics-Preserving Evasion of LLM Vulnerability Detectors

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents

Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis

Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias

Emergent Formal Verification: How an Autonomous AI Ecosystem Independently Discovered SMT-Based Safety Across Six Domains

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Browse all 10 papers