{"total":20,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2408.05868","title":"LaWa: Using Latent Space for In-Generation Image Watermarking","created":"2024-08-11","cited_by_count":28,"area":"safety"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"area":"safety"},{"id":"2407.08441","title":"Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation","created":"2024-07-11","cited_by_count":9,"area":"safety"},{"id":"2402.16889","title":"Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation","created":"2024-02-23","cited_by_count":3,"area":"safety"},{"id":"2604.09544","title":"Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2504.19019","title":"Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs","created":"2025-04-26","cited_by_count":2,"area":"safety"},{"id":"2505.15175","title":"A Linear Approach to Data Poisoning","created":"2025-05-21","cited_by_count":2,"area":"safety"},{"id":"2510.04528","title":"Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"id":"2603.10068","title":"ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models","created":"2026-03-10","cited_by_count":1,"area":"safety"},{"id":"2603.22870","title":"Designing to Forget: Deep Semi-parametric Models for Unlearning","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2604.10460","title":"Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection","created":"2026-04-12","cited_by_count":1,"area":"safety"},{"id":"2409.10570","title":"Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking","created":"2024-09-14","cited_by_count":0,"area":"safety"},{"id":"2503.15205","title":"A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models","created":"2025-03-19","cited_by_count":0,"area":"safety"},{"id":"2511.18790","title":"RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM Moderation","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2606.09388","title":"Distilling Safe LLM Systems via Soft Prompts for On Device Settings","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.27373","title":"RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation","created":"2026-07-29","cited_by_count":0,"area":"safety"},{"id":"2608.20338","title":"ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models","created":"2026-08-20","cited_by_count":0,"area":"safety"}],"next_cursor":null}