{"total":23,"rows":[{"id":"2103.15543","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","created":"2021-03-29","cited_by_count":105,"area":"safety"},{"id":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73,"area":"safety"},{"id":"2301.02496","title":"Stealthy Backdoor Attack for Code Models","created":"2023-01-06","cited_by_count":49,"area":"safety"},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"id":"2409.00089","title":"Watermarking Techniques for Large Language Models: A Survey","created":"2024-08-26","cited_by_count":23,"area":"safety"},{"id":"2107.05243","title":"Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning","created":"2021-07-12","cited_by_count":21,"area":"safety"},{"id":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"area":"safety"},{"id":"2204.06106","title":"Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms","created":"2022-04-12","cited_by_count":19,"area":"safety"},{"id":"2406.19845","title":"Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection","created":"2024-06-28","cited_by_count":17,"area":"safety"},{"id":"2301.10412","title":"BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing","created":"2023-01-25","cited_by_count":16,"area":"safety"},{"id":"2303.14325","title":"Backdoor Attacks with Input-unique Triggers in NLP","created":"2023-03-25","cited_by_count":12,"area":"safety"},{"id":"2210.17029","title":"Poison Attack and Defense on Deep Source Code Processing Models","created":"2022-10-31","cited_by_count":11,"area":"safety"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2407.15009","title":"RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words","created":"2024-06-11","cited_by_count":4,"area":"safety"},{"id":"2601.21283","title":"DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher","created":"2026-01-29","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":"2512.16904","title":"How Good is Post-Hoc Watermarking With Language Model Rephrasing?","created":"2025-12-18","cited_by_count":2,"area":"safety"},{"id":"2308.15673","title":"MDTD: A Multi Domain Trojan Detector for Deep Neural Networks","created":"2023-08-30","cited_by_count":1,"area":"safety"},{"id":"2605.19227","title":"Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models","created":"2026-05-19","cited_by_count":1,"area":"safety"},{"id":"2603.01550","title":"Extracting Training Dialogue Data from Large Language Model based Task Bots","created":"2026-03-02","cited_by_count":0,"area":"safety"},{"id":"2609.37367","title":"Backdoor Mitigation in Decentralized LLM Fine-Tuning","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.15725","title":"SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification","created":"2026-10-11","cited_by_count":0,"area":"safety"}],"next_cursor":null}