{"total":14,"rows":[{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"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":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2410.21750","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","created":"2024-10-29","cited_by_count":4,"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":"2601.21564","title":"Representation Unlearning: Forgetting through Information Compression","created":"2026-01-29","cited_by_count":2,"area":"safety"},{"id":"2509.25843","title":"ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2604.18970","title":"Mechanistic Anomaly Detection via Functional Attribution","created":"2026-04-21","cited_by_count":1,"area":"safety"},{"id":"2512.03437","title":"Grokked Models are Better Unlearners","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2602.05635","title":"Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias","created":"2026-02-05","cited_by_count":0,"area":"safety"},{"id":"2604.23130","title":"From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks","created":"2026-04-25","cited_by_count":0,"area":"safety"},{"id":"2609.09553","title":"Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":"safety"},{"id":"2610.07334","title":"Weight Oracles: Reading Neural Network Weights with Language Models","created":"2026-10-05","cited_by_count":0,"area":"safety"}],"next_cursor":null}