{"total":33,"rows":[{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"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":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2602.03085","title":"The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers","created":"2026-02-03","cited_by_count":14,"area":"safety"},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11,"area":"safety"},{"id":"2509.21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models","created":"2025-09-26","cited_by_count":10,"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":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2503.05445","title":"Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks","created":"2025-03-07","cited_by_count":6,"area":"safety"},{"id":"2510.10265","title":"Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models","created":"2025-10-11","cited_by_count":6,"area":"safety"},{"id":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"safety"},{"id":"2601.06305","title":"Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models","created":"2026-01-09","cited_by_count":4,"area":"safety"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2510.05169","title":"From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs","created":"2025-10-05","cited_by_count":2,"area":"safety"},{"id":"2508.21004","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2512.10998","title":"SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models","created":"2025-12-10","cited_by_count":1,"area":"safety"},{"id":"2601.12460","title":"TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning","created":"2026-01-18","cited_by_count":1,"area":"safety"},{"id":"2602.13427","title":"Backdooring Bias in Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"safety"},{"id":"2605.12529","title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","created":"2026-04-15","cited_by_count":1,"area":"safety"},{"id":"2605.25073","title":"Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions","created":"2026-05-24","cited_by_count":1,"area":"safety"},{"id":"2606.11648","title":"Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs","created":"2026-06-10","cited_by_count":1,"area":"safety"},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2509.16203","title":"Inverting Trojans in LLMs","created":"2025-09-19","cited_by_count":0,"area":"safety"},{"id":"2602.06887","title":"Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2604.24162","title":"Defusing the Trigger: Tail-Risk-Informed Attention Rebalancing for LLM Backdoor Mitigation","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2606.29646","title":"Fuzzing Large Language Models to Elicit Hidden Behaviours","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2606.31309","title":"CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2608.30403","title":"Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.00351","title":"Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2610.00348","title":"Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.14701","title":"Towards Merging-conditional Backdoor Unalignment against Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"},{"id":"2610.18430","title":"FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}