{"total":78,"rows":[{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116,"area":"safety"},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2305.01219","title":"Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models","created":"2023-05-02","cited_by_count":94,"area":"safety"},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91,"area":"safety"},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"area":"safety"},{"id":"2406.12038","title":"Soft Prompting for Unlearning in Large Language Models","created":"2024-06-17","cited_by_count":46,"area":"safety"},{"id":"2310.12439","title":"PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models","created":"2023-10-19","cited_by_count":42,"area":"safety"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2403.01251","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","created":"2024-03-02","cited_by_count":37,"area":"safety"},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2309.13256","title":"Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks","created":"2023-09-23","cited_by_count":33,"area":"safety"},{"id":"2507.07974","title":"Defending Against Prompt Injection With a Few DefensiveTokens","created":"2025-07-10","cited_by_count":33,"area":"safety"},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27,"area":"safety"},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2405.20778","title":"Improved Generation of Adversarial Examples Against Safety-aligned LLMs","created":"2024-05-28","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":"2501.03544","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","created":"2025-01-07","cited_by_count":17,"area":"safety"},{"id":"2412.08615","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","created":"2024-12-11","cited_by_count":15,"area":"safety"},{"id":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2412.16504","title":"Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions","created":"2024-12-21","cited_by_count":14,"area":"safety"},{"id":"2405.07667","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","created":"2024-05-13","cited_by_count":12,"area":"safety"},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12,"area":"safety"},{"id":"2406.07778","title":"A Study of Backdoors in Instruction Fine-tuned Language Models","created":"2024-06-12","cited_by_count":11,"area":"safety"},{"id":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","cited_by_count":10,"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":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9,"area":"safety"},{"id":"2312.04748","title":"Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks","created":"2023-12-07","cited_by_count":9,"area":"safety"},{"id":"2407.12281","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","created":"2024-07-17","cited_by_count":9,"area":"safety"},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"area":"safety"},{"id":"2305.09574","title":"UOR: Universal Backdoor Attacks on Pre-trained Language Models","created":"2023-05-16","cited_by_count":8,"area":"safety"},{"id":"2310.11970","title":"Quantifying Privacy Risks of Prompts in Visual Prompt Learning","created":"2023-10-18","cited_by_count":8,"area":"safety"},{"id":"2512.07375","title":"LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples","created":"2025-12-08","cited_by_count":8,"area":"safety"},{"id":"2406.19395","title":"Dataset Size Recovery from LoRA Weights","created":"2024-06-27","cited_by_count":7,"area":"safety"},{"id":"2306.04535","title":"PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts","created":"2023-06-07","cited_by_count":6,"area":"safety"},{"id":"2504.14738","title":"PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines","created":"2025-04-20","cited_by_count":6,"area":"safety"},{"id":"2304.14364","title":"CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants","created":"2023-04-27","cited_by_count":5,"area":"safety"},{"id":"2402.18945","title":"SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer","created":"2024-02-29","cited_by_count":5,"area":"safety"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2505.15674","title":"UniErase: Towards Balanced and Precise Unlearning in Language Models","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2506.15751","title":"Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts","created":"2025-06-18","cited_by_count":5,"area":"safety"},{"id":"2310.07632","title":"Prompt Backdoors in Visual Prompt Learning","created":"2023-10-11","cited_by_count":4,"area":"safety"},{"id":"2405.19563","title":"Unlearning Climate Misinformation in Large Language Models","created":"2024-05-29","cited_by_count":4,"area":"safety"},{"id":"2405.20015","title":"Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak","created":"2024-05-30","cited_by_count":4,"area":"safety"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"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":"2305.16371","title":"INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition","created":"2023-05-25","cited_by_count":3,"area":"safety"},{"id":"2506.18325","title":"NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation","created":"2025-06-23","cited_by_count":3,"area":"safety"},{"id":"2512.16292","title":"In-Context Probing for Membership Inference in Fine-Tuned Language Models","created":"2025-12-18","cited_by_count":3,"area":"safety"},{"id":"2604.21251","title":"CAP: Controllable Alignment Prompting for Unlearning in LLMs","created":"2026-04-23","cited_by_count":3,"area":"safety"},{"id":"2404.11056","title":"LMEraser: Large Model Unlearning through Adaptive Prompt Tuning","created":"2024-04-17","cited_by_count":2,"area":"safety"},{"id":"2406.04478","title":"PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning","created":"2024-06-06","cited_by_count":2,"area":"safety"},{"id":"2409.17946","title":"Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs","created":"2024-09-26","cited_by_count":2,"area":"safety"},{"id":"2502.15836","title":"Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2508.04281","title":"Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy","created":"2025-08-06","cited_by_count":2,"area":"safety"},{"id":"2310.00648","title":"PETA: Parameter-Efficient Trojan Attacks","created":"2023-10-01","cited_by_count":1,"area":"safety"},{"id":"2509.15230","title":"Pre-Forgettable Models: Prompt Learning as a Native Mechanism for Unlearning","created":"2025-09-05","cited_by_count":1,"area":"safety"},{"id":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2601.06641","title":"Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning","created":"2026-01-10","cited_by_count":1,"area":"safety"},{"id":"2404.00461","title":"Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning","created":"2024-03-30","cited_by_count":0,"area":"safety"},{"id":"2511.12735","title":"Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning","created":"2025-11-16","cited_by_count":0,"area":"safety"},{"id":"2512.08123","title":"Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation","created":"2025-12-09","cited_by_count":0,"area":"safety"},{"id":"2512.08131","title":"Universal Adversarial Suffixes for Language Models Using Reinforcement Learning with Calibrated Reward","created":"2025-12-09","cited_by_count":0,"area":"safety"},{"id":"2601.10045","title":"Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD","created":"2026-01-15","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":"2605.19478","title":"Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2605.31246","title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2606.17123","title":"LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2607.27836","title":"Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration","created":"2026-07-30","cited_by_count":0,"area":"safety"},{"id":"2608.09624","title":"Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2608.20991","title":"Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models","created":"2026-08-21","cited_by_count":0,"area":"safety"},{"id":"2608.23873","title":"Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors","created":"2026-08-24","cited_by_count":0,"area":"safety"},{"id":"2609.36657","title":"Constitutional adapters: Inference-time interventions for misalignment and misuse","created":"2026-09-29","cited_by_count":0,"area":"safety"}],"next_cursor":null}