{"total":22,"rows":[{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2410.20911","title":"Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks","created":"2024-10-28","cited_by_count":15,"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":"2603.10521","title":"IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs","created":"2026-03-11","cited_by_count":15,"area":"safety"},{"id":"2507.07341","title":"On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment","created":"2025-07-09","cited_by_count":12,"area":"safety"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2602.13284","title":"Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook","created":"2026-02-07","cited_by_count":10,"area":"safety"},{"id":"2402.05723","title":"In-Context Learning Can Re-learn Forbidden Tasks","created":"2024-02-08","cited_by_count":5,"area":"safety"},{"id":"2603.00991","title":"Tracking Capabilities for Safer Agents","created":"2026-03-01","cited_by_count":4,"area":"safety"},{"id":"2207.13572","title":"Membership Inference Attacks via Adversarial Examples","created":"2022-07-27","cited_by_count":2,"area":"safety"},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2512.21110","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2607.01277","title":"Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety","created":"2026-07-01","cited_by_count":1,"area":"safety"},{"id":"2506.11615","title":"Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments","created":"2025-06-13","cited_by_count":0,"area":"safety"},{"id":"2512.03047","title":"Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models","created":"2025-11-19","cited_by_count":0,"area":"safety"},{"id":"2512.08185","title":"A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties","created":"2025-12-09","cited_by_count":0,"area":"safety"},{"id":"2601.06033","title":"How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape","created":"2025-11-10","cited_by_count":0,"area":"safety"},{"id":"2610.08540","title":"Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements","created":"2026-10-06","cited_by_count":0,"area":"safety"}],"next_cursor":null}