ML Security Papers

LS10

Benchmarks & Evaluation

Datasets and benchmarks for LLM4SEC

53 papers Browse all papers

Monthly publications

Paper types

benchmark 24

attack 13

tool 10

defense 4

survey 2

Domains

nlp 53

multimodal 5

vision 2

audio 1

reinforcement-learning 1

Co-occurring categories

Other OWASP categories that appear on the same papers

LLM01 Prompt Injection

LS06 Red-Team Agents

LLM08 Excessive Agency

LS07 Blue-Team Agents

ML01 Input Manipulation Attack

LS01 Vulnerability Discovery

LLM07 Insecure Plugin Design

ML06 AI Supply Chain Attacks

LS05 Triage & Prioritization

Top cited papers

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

Anecdoctoring: Automated Red-Teaming Across Language and Place

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models

Async Control: Stress-testing Asynchronous Control Measures for LLM Agents

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

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

RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning

Browse all 53 papers