Browse State-of-the-Art › Red Teaming › Papers, page 2

Red Teaming

Papers archive 2025-07-28

archive papers tagged: 251 · with a code link: 110 · where Syntology ran a sample: 57 (45 with a run with no instrument failure, 12 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (57 of 251 tagged: 45 with a run with no instrument failure, 12 where every run was a failure of Syntology's instrument)

Page 2 of 3: papers 101 to 200 of 251, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. Abstracts are on each paper's page.

• Attack Prompt Generation for Red Teaming and Defending Large Language Models
  19 Oct 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
• ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models
  14 Oct 2023 1 repository listed
• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
  5 Oct 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
• No Offense Taken: Eliciting Offensiveness from Language Models
  2 Oct 2023 1 repository listed
• Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
  12 Sep 2023 1 repository listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
• GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
  12 Aug 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
• XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
  2 Aug 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
• Jailbroken: How Does LLM Safety Training Fail?
  5 Jul 2023 1 repository listed
• Query-Efficient Black-Box Red Teaming via Bayesian Optimization
  27 May 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
• Red Teaming Language Models with Language Models
  7 Feb 2022 1 repository listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
• STACK: Adversarial Attacks on LLM Safeguard Pipelines
  30 Jun 2025 0 repositories listed
• GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
  11 Jun 2025 0 repositories listed
• Effective Red-Teaming of Policy-Adherent Agents
  11 Jun 2025 0 repositories listed
• Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
  8 Jun 2025 0 repositories listed
• Red Teaming AI Policy: A Taxonomy of Avoision and the EU AI Act
  2 Jun 2025 0 repositories listed
• A Red Teaming Roadmap Towards System-Level Safety
  30 May 2025 0 repositories listed
• A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming
  30 May 2025 0 repositories listed
• Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
  30 May 2025 0 repositories listed
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
  29 May 2025 0 repositories listed
• SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
  29 May 2025 0 repositories listed
• Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
  27 May 2025 0 repositories listed
• GhostPrompt: Jailbreaking Text-to-image Generative Models based on Dynamic Optimization
  25 May 2025 0 repositories listed
• Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
  24 May 2025 0 repositories listed
• Towards medical AI misalignment: a preliminary study
  22 May 2025 0 repositories listed
• RRTL: Red Teaming Reasoning Large Language Models in Tool Learning
  21 May 2025 0 repositories listed
• EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection
  20 May 2025 0 repositories listed
• "Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs
  20 May 2025 0 repositories listed
• Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
  20 May 2025 0 repositories listed
• CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
  19 May 2025 0 repositories listed
• LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
  16 May 2025 0 repositories listed
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
  9 May 2025 0 repositories listed
• Offensive Security for AI Systems: Concepts, Practices, and Applications
  9 May 2025 0 repositories listed
• Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods
  8 May 2025 0 repositories listed
• DMRL: Data- and Model-aware Reward Learning for Data Extraction
  7 May 2025 0 repositories listed
• Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
  7 May 2025 0 repositories listed
• Red Teaming Large Language Models for Healthcare
  1 May 2025 0 repositories listed
• When Testing AI Tests Us: Safeguarding Mental Health on the Digital Frontlines
  29 Apr 2025 0 repositories listed
• RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
  25 Apr 2025 0 repositories listed
• Understanding and Mitigating Risks of Generative AI in Financial Services
  25 Apr 2025 0 repositories listed
• ELAB: Extensive LLM Alignment Benchmark in Persian Language
  17 Apr 2025 0 repositories listed
• X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
  15 Apr 2025 0 repositories listed
• Multi-lingual Multi-turn Automated Red Teaming for LLMs
  4 Apr 2025 0 repositories listed
• Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
  2 Apr 2025 0 repositories listed
• Red Teaming with Artificial Intelligence-Driven Cyberattacks: A Scoping Review
  25 Mar 2025 0 repositories listed
• AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
  20 Mar 2025 0 repositories listed
• MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
  19 Mar 2025 0 repositories listed
• A Framework for Evaluating Emerging Cyberattack Capabilities of AI
  14 Mar 2025 0 repositories listed
• Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization
  14 Mar 2025 0 repositories listed
• Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives
  13 Mar 2025 0 repositories listed
• JBFuzz: Jailbreaking LLMs Efficiently and Effectively Using Fuzzing
  12 Mar 2025 0 repositories listed
• MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
  8 Mar 2025 0 repositories listed
• Reinforced Diffuser for Red Teaming Large Vision-Language Models
  8 Mar 2025 0 repositories listed
• Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
  6 Mar 2025 0 repositories listed
• LLM-Safety Evaluations Lack Robustness
  4 Mar 2025 0 repositories listed
• Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models
  3 Mar 2025 0 repositories listed
• Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
  22 Feb 2025 0 repositories listed
• Fast Proxies for LLM Robustness Evaluation
  14 Feb 2025 0 repositories listed
• A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management
  10 Feb 2025 0 repositories listed
• Predictive Red Teaming: Breaking Policies Without Breaking Robots
  10 Feb 2025 0 repositories listed
• KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
  5 Feb 2025 0 repositories listed
• Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
  31 Jan 2025 0 repositories listed
• Playing Devil's Advocate: Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models
  14 Jan 2025 0 repositories listed
• Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints
  14 Jan 2025 0 repositories listed
• Lessons From Red Teaming 100 Generative AI Products
  13 Jan 2025 0 repositories listed
• Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
  9 Jan 2025 0 repositories listed
• Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
  3 Jan 2025 0 repositories listed
• Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
  24 Dec 2024 0 repositories listed
• OpenAI o1 System Card
  21 Dec 2024 0 repositories listed
• POEX: Understanding and Mitigating Policy Executable Jailbreak Attacks against Embodied AI
  21 Dec 2024 0 repositories listed
• AI red-teaming is a sociotechnical challenge: on values, labor, and harms
  12 Dec 2024 0 repositories listed
• Embodied Red Teaming for Auditing Robotic Foundation Models
  27 Nov 2024 0 repositories listed
• In-Context Experience Replay Facilitates Safety Red-Teaming of Text-to-Image Diffusion Models
  25 Nov 2024 0 repositories listed
• LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
  13 Nov 2024 0 repositories listed
• Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs
  31 Oct 2024 0 repositories listed
• AdvAgent: Controllable Blackbox Red-teaming on Web Agents
  22 Oct 2024 0 repositories listed
• LLM-Assisted Red Teaming of Diffusion Models through "Failures Are Fated, But Can Be Faded"
  22 Oct 2024 0 repositories listed
• Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis
  21 Oct 2024 0 repositories listed
• A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation
  15 Oct 2024 0 repositories listed
• VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment
  12 Oct 2024 0 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)
• Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations
  9 Oct 2024 0 repositories listed
• SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
  3 Oct 2024 0 repositories listed
• Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
  2 Oct 2024 0 repositories listed
• Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
  23 Sep 2024 0 repositories listed
• Jailbreaking Large Language Models with Symbolic Mathematics
  17 Sep 2024 0 repositories listed
• Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols
  12 Sep 2024 0 repositories listed
• Exploring Straightforward Conversational Red-Teaming
  7 Sep 2024 0 repositories listed
• Conversational Complexity for Assessing Risk in Large Language Models
  2 Sep 2024 0 repositories listed
• Testing and Evaluation of Large Language Models: Correctness, Non-Toxicity, and Fairness
  31 Aug 2024 0 repositories listed
• Atoxia: Red-teaming Large Language Models with Target Toxic Answers
  27 Aug 2024 0 repositories listed
• DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
  18 Aug 2024 0 repositories listed
• SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
  14 Aug 2024 0 repositories listed
• h4rm3l: A language for Composable Jailbreak Attack Synthesis
  9 Aug 2024 0 repositories listed
• Can Large Language Models Automatically Jailbreak GPT-4V?
  23 Jul 2024 0 repositories listed
• RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
  23 Jul 2024 0 repositories listed
• Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems
  22 Jul 2024 0 repositories listed
• Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts
  21 Jul 2024 0 repositories listed
• Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
  18 Jul 2024 0 repositories listed
• Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
  17 Jul 2024 0 repositories listed
• The Human Factor in AI Red Teaming: Perspectives from Social and Collaborative Computing
  10 Jul 2024 0 repositories listed
• Purple-teaming LLMs with Adversarial Defender Training
  1 Jul 2024 0 repositories listed

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page has not changed since 2026-09-28, the first build that kept a record date for it; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.