Papers with Code 아카이브
Red Teaming
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
STACK: Adversarial Attacks on LLM Safeguard Pipelines
We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
Effective Red-Teaming of Policy-Adherent Agents
GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming
RedDebate: Safer Responses through Multi-Agent Red Teaming Debates
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Red Teaming AI Policy: A Taxonomy of Avoision and the EU AI Act
A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis
Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
A Red Teaming Roadmap Towards System-Level Safety
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
Capability-Based Scaling Laws for LLM Red-Teaming
GhostPrompt: Jailbreaking Text-to-image Generative Models based on Dynamic Optimization
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
Towards medical AI misalignment: a preliminary study
RRTL: Red Teaming Reasoning Large Language Models in Tool Learning
"Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs
EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
Offensive Security for AI Systems: Concepts, Practices, and Applications
Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods
Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
DMRL: Data- and Model-aware Reward Learning for Data Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.