{"total":31,"rows":[{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"id":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11,"area":"safety"},{"id":"2406.12329","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","created":"2024-06-18","cited_by_count":10,"area":"safety"},{"id":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","cited_by_count":10,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2507.01321","title":"ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks","created":"2025-07-02","cited_by_count":9,"area":"safety"},{"id":"2508.01365","title":"ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models","created":"2025-08-02","cited_by_count":9,"area":"safety"},{"id":"2410.13274","title":"Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning","created":"2024-10-17","cited_by_count":8,"area":"safety"},{"id":"2505.16530","title":"DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection","created":"2025-05-22","cited_by_count":8,"area":"safety"},{"id":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2504.05689","title":"Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2505.03501","title":"BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"safety"},{"id":"2510.07775","title":"The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs","created":"2025-10-09","cited_by_count":2,"area":"safety"},{"id":"2603.02436","title":"TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":"safety"},{"id":"2607.18639","title":"Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs","created":"2026-07-21","cited_by_count":2,"area":"safety"},{"id":"2508.06153","title":"SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs","created":"2025-08-08","cited_by_count":1,"area":"safety"},{"id":"2605.08765","title":"Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2509.25743","title":"Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space","created":"2025-09-30","cited_by_count":0,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2604.14644","title":"CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge","created":"2026-04-16","cited_by_count":0,"area":"safety"},{"id":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2606.04612","title":"Hybrid Adversarial Defence for Natural Language Understanding Tasks","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2606.23313","title":"Uncertainty-based Debiasing and Unlearning for Decontamination","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2609.01023","title":"AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}