{"total":81,"rows":[{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279,"area":"safety"},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158,"area":"safety"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2305.06535","title":"KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment","created":"2023-05-11","cited_by_count":99,"area":"safety"},{"id":"2204.07655","title":"Deep Unlearning via Randomized Conditionally Independent Hessians","created":"2022-04-15","cited_by_count":84,"area":"safety"},{"id":"2403.01446","title":"GuardT2I: Defending Text-to-Image Models from Adversarial Prompts","created":"2024-03-03","cited_by_count":62,"area":"safety"},{"id":"2307.15992","title":"Towards Codable Watermarking for Injecting Multi-bits Information to LLMs","created":"2023-07-29","cited_by_count":54,"area":"safety"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2406.11036","title":"garak: A Framework for Security Probing Large Language Models","created":"2024-06-16","cited_by_count":49,"area":"safety"},{"id":"2202.05749","title":"Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense","created":"2022-02-11","cited_by_count":47,"area":"safety"},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37,"area":"safety"},{"id":"2109.13236","title":"FedIPR: Ownership Verification for Federated Deep Neural Network Models","created":"2021-09-27","cited_by_count":36,"area":"safety"},{"id":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"id":"2403.14719","title":"Bypassing LLM Watermarks with Color-Aware Substitutions","created":"2024-03-19","cited_by_count":28,"area":"safety"},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"id":"2311.00172","title":"Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield","created":"2023-10-31","cited_by_count":25,"area":"safety"},{"id":"2206.01832","title":"Kallima: A Clean-label Framework for Textual Backdoor Attacks","created":"2022-06-03","cited_by_count":24,"area":"safety"},{"id":"2212.10440","title":"Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data","created":"2022-12-20","cited_by_count":22,"area":"safety"},{"id":"2406.12354","title":"Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models","created":"2024-06-18","cited_by_count":20,"area":"safety"},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2110.08247","title":"Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks","created":"2021-10-15","cited_by_count":18,"area":"safety"},{"id":"2406.14796","title":"MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning","created":"2024-06-21","cited_by_count":17,"area":"safety"},{"id":"2503.07384","title":"Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs","created":"2025-03-10","cited_by_count":10,"area":"safety"},{"id":"2601.03190","title":"Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning","created":"2026-01-06","cited_by_count":10,"area":"safety"},{"id":"2505.14316","title":"Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion","created":"2025-05-20","cited_by_count":9,"area":"safety"},{"id":"2303.01742","title":"NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning","created":"2023-03-03","cited_by_count":8,"area":"safety"},{"id":"2312.07200","title":"Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models","created":"2023-12-12","cited_by_count":8,"area":"safety"},{"id":"2504.15548","title":"LLM-based Semantic Augmentation for Harmful Content Detection","created":"2025-04-22","cited_by_count":7,"area":"safety"},{"id":"2409.14200","title":"Data-centric NLP Backdoor Defense from the Lens of Memorization","created":"2024-09-21","cited_by_count":6,"area":"safety"},{"id":"2506.03142","title":"Not All Tokens Are Meant to Be Forgotten","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6,"area":"safety"},{"id":"2602.15143","title":"Protecting Language Models Against Unauthorized Distillation through Trace Rewriting","created":"2026-02-16","cited_by_count":6,"area":"safety"},{"id":"2507.07871","title":"Mitigating Watermark Forgery in Generative Models via Randomized Key Selection","created":"2025-07-10","cited_by_count":4,"area":"safety"},{"id":"2512.06899","title":"Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models","created":"2025-12-07","cited_by_count":4,"area":"safety"},{"id":"2401.10375","title":"Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities","created":"2024-01-18","cited_by_count":3,"area":"safety"},{"id":"2402.07689","title":"OrderBkd: Textual backdoor attack through repositioning","created":"2024-02-12","cited_by_count":3,"area":"safety"},{"id":"2409.01952","title":"Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor","created":"2024-09-03","cited_by_count":3,"area":"safety"},{"id":"2411.08443","title":"Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA","created":"2024-11-13","cited_by_count":3,"area":"safety"},{"id":"2508.14128","title":"CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection","created":"2025-08-19","cited_by_count":3,"area":"safety"},{"id":"2602.07235","title":"ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport","created":"2026-02-06","cited_by_count":3,"area":"safety"},{"id":"2603.19302","title":"Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning","created":"2026-03-11","cited_by_count":3,"area":"safety"},{"id":"2408.11587","title":"Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks","created":"2024-08-21","cited_by_count":2,"area":"safety"},{"id":"2503.22539","title":"Efficient Verified Machine Unlearning For Distillation","created":"2025-03-28","cited_by_count":2,"area":"safety"},{"id":"2201.02993","title":"Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing","created":"2022-01-09","cited_by_count":1,"area":"safety"},{"id":"2211.09717","title":"UPTON: Preventing Authorship Leakage from Public Text Release via Data Poisoning","created":"2022-11-17","cited_by_count":1,"area":"safety"},{"id":"2306.03600","title":"Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations","created":"2023-06-06","cited_by_count":1,"area":"safety"},{"id":"2401.11365","title":"Confidence Preservation Property in Knowledge Distillation Abstractions","created":"2024-01-21","cited_by_count":1,"area":"safety"},{"id":"2407.04179","title":"Defense Against Syntactic Textual Backdoor Attacks with Token Substitution","created":"2024-07-04","cited_by_count":1,"area":"safety"},{"id":"2503.03502","title":"Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension","created":"2025-03-05","cited_by_count":1,"area":"safety"},{"id":"2504.02486","title":"We Need Improved Data Curation and Attribution in AI for Scientific Discovery","created":"2025-04-03","cited_by_count":1,"area":"safety"},{"id":"2505.11837","title":"On Membership Inference Attacks in Knowledge Distillation","created":"2025-05-17","cited_by_count":1,"area":"safety"},{"id":"2505.13362","title":"Dynamic Probabilistic Noise Injection for Membership Inference Defense","created":"2025-05-19","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":"2601.12104","title":"Powerful Training-Free Membership Inference Against Autoregressive Language Models","created":"2026-01-17","cited_by_count":1,"area":"safety"},{"id":"2602.18583","title":"Luna-2: Scalable Single-Token Evaluation with Small Language Models","created":"2026-02-20","cited_by_count":1,"area":"safety"},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2604.27666","title":"VOW: Verifiable and Oblivious Watermark Detection for Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"safety"},{"id":"2605.23175","title":"Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection","created":"2026-05-22","cited_by_count":1,"area":"safety"},{"id":"2605.29434","title":"AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2411.03363","title":"TDDBench: A Benchmark for Training data detection","created":"2024-11-05","cited_by_count":0,"area":"safety"},{"id":"2503.18117","title":"Detection of Somali-written Fake News and Toxic Messages on the Social Media Using Transformer-based Language Models","created":"2025-03-23","cited_by_count":0,"area":"safety"},{"id":"2505.08804","title":"TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis","created":"2025-05-11","cited_by_count":0,"area":"safety"},{"id":"2507.12185","title":"Jailbreaking Generative AI: Multivector Phishing Threats and Transformer based Defenses","created":"2025-07-16","cited_by_count":0,"area":"safety"},{"id":"2508.15934","title":"Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification","created":"2025-08-21","cited_by_count":0,"area":"safety"},{"id":"2511.06794","title":"Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning","created":"2025-11-10","cited_by_count":0,"area":"safety"},{"id":"2512.01498","title":"No Trust Issues Here: A Technical Report on the Winning Solutions for the Rayan AI Contest","created":"2025-12-01","cited_by_count":0,"area":"safety"},{"id":"2512.16182","title":"DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack","created":"2025-12-18","cited_by_count":0,"area":"safety"},{"id":"2601.20885","title":"What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models","created":"2026-01-27","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":"2607.04339","title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","created":"2026-07-05","cited_by_count":0,"area":"safety"},{"id":"2607.17550","title":"(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure","created":"2026-07-20","cited_by_count":0,"area":"safety"},{"id":"2608.01094","title":"Lethe: How Hard Is It to Forget? A Benchmark for Federated Unlearning in Medical Imaging","created":"2026-08-02","cited_by_count":0,"area":"safety"},{"id":"2608.29589","title":"Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.10935","title":"Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2","created":"2026-09-10","cited_by_count":0,"area":"safety"},{"id":"2609.22981","title":"Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach","created":"2026-09-19","cited_by_count":0,"area":"safety"},{"id":"2609.35881","title":"GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation","created":"2026-09-27","cited_by_count":0,"area":"safety"}],"next_cursor":null}