{"total":80,"rows":[{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143,"area":"safety"},{"id":"2403.04957","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","created":"2024-03-07","cited_by_count":119,"area":"safety"},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"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":"2110.02467","title":"BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models","created":"2021-10-06","cited_by_count":85,"area":"safety"},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"area":"safety"},{"id":"2104.08305","title":"Membership Inference Attack Susceptibility of Clinical Language Models","created":"2021-04-16","cited_by_count":52,"area":"safety"},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"id":"2210.07543","title":"Watermarking Pre-trained Language Models with Backdooring","created":"2022-10-14","cited_by_count":50,"area":"safety"},{"id":"2407.20516","title":"Machine Unlearning in Generative AI: A Survey","created":"2024-07-30","cited_by_count":49,"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":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2212.09573","title":"Privacy Adhering Machine Un-learning in NLP","created":"2022-12-19","cited_by_count":36,"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":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"area":"safety"},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"id":"2406.16257","title":"Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning","created":"2024-06-24","cited_by_count":27,"area":"safety"},{"id":"2306.08350","title":"Multi-target Backdoor Attacks for Code Pre-trained Models","created":"2023-06-14","cited_by_count":23,"area":"safety"},{"id":"2402.02160","title":"Data Poisoning for In-context Learning","created":"2024-02-03","cited_by_count":21,"area":"safety"},{"id":"2410.14827","title":"Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment","created":"2024-10-18","cited_by_count":21,"area":"safety"},{"id":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2202.08578","title":"An Equivalence Between Data Poisoning and Byzantine Gradient Attacks","created":"2022-02-17","cited_by_count":16,"area":"safety"},{"id":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15,"area":"safety"},{"id":"2407.04411","title":"Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs","created":"2024-07-05","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":"2311.09816","title":"Downstream Trade-offs of a Family of Text Watermarks","created":"2023-11-16","cited_by_count":14,"area":"safety"},{"id":"2409.01193","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","created":"2024-09-02","cited_by_count":13,"area":"safety"},{"id":"2305.19607","title":"Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems","created":"2023-05-31","cited_by_count":11,"area":"safety"},{"id":"2512.21008","title":"GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs","created":"2025-12-24","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":"2412.00765","title":"SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts","created":"2024-12-01","cited_by_count":10,"area":"safety"},{"id":"2501.12210","title":"You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense","created":"2025-01-21","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":"2305.04547","title":"Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias","created":"2023-05-08","cited_by_count":8,"area":"safety"},{"id":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"area":"safety"},{"id":"2406.18725","title":"Jailbreaking LLMs with Arabic Transliteration and Arabizi","created":"2024-06-26","cited_by_count":7,"area":"safety"},{"id":"2505.23561","title":"Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2508.08211","title":"SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders","created":"2025-08-11","cited_by_count":7,"area":"safety"},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2411.03806","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","created":"2024-11-06","cited_by_count":6,"area":"safety"},{"id":"2509.25673","title":"Mitigating Biases in Language Models via Bias Unlearning","created":"2025-09-30","cited_by_count":6,"area":"safety"},{"id":"2502.13996","title":"Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis","created":"2025-02-19","cited_by_count":5,"area":"safety"},{"id":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2401.00996","title":"Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment","created":"2024-01-02","cited_by_count":4,"area":"safety"},{"id":"2411.06611","title":"vTune: Verifiable Fine-Tuning for LLMs Through Backdooring","created":"2024-11-10","cited_by_count":4,"area":"safety"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2505.12871","title":"Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?","created":"2025-05-19","cited_by_count":4,"area":"safety"},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","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":"2311.17429","title":"TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4","created":"2023-11-29","cited_by_count":3,"area":"safety"},{"id":"2502.06653","title":"In-Context Learning (and Unlearning) of Length Biases","created":"2025-02-10","cited_by_count":3,"area":"safety"},{"id":"2507.23453","title":"Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems","created":"2025-07-31","cited_by_count":3,"area":"safety"},{"id":"2508.17233","title":"Module-Aware Parameter-Efficient Machine Unlearning on Transformers","created":"2025-08-24","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":"2508.17681","title":"Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery","created":"2025-08-25","cited_by_count":2,"area":"safety"},{"id":"2401.11365","title":"Confidence Preservation Property in Knowledge Distillation Abstractions","created":"2024-01-21","cited_by_count":1,"area":"safety"},{"id":"2403.05842","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","created":"2024-03-09","cited_by_count":1,"area":"safety"},{"id":"2406.05364","title":"Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models","created":"2024-06-08","cited_by_count":1,"area":"safety"},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2602.06623","title":"Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2604.04231","title":"Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization","created":"2026-04-05","cited_by_count":1,"area":"safety"},{"id":"2605.18993","title":"Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic","created":"2026-05-18","cited_by_count":1,"area":"safety"},{"id":"2211.05371","title":"MSDT: Masked Language Model Scoring Defense in Text Domain","created":"2022-11-10","cited_by_count":0,"area":"safety"},{"id":"2311.10236","title":"Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study","created":"2023-11-16","cited_by_count":0,"area":"safety"},{"id":"2411.03363","title":"TDDBench: A Benchmark for Training data detection","created":"2024-11-05","cited_by_count":0,"area":"safety"},{"id":"2504.08757","title":"A Framework for Lightweight Responsible Prompting Recommendation","created":"2025-03-29","cited_by_count":0,"area":"safety"},{"id":"2511.23393","title":"FedSGT: Exact Federated Unlearning via Sequential Group-based Training","created":"2025-11-28","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":"2602.18483","title":"Red Teaming LLMs as Socio-Technical Practice: From Exploration and Data Creation to Evaluation","created":"2026-02-10","cited_by_count":0,"area":"safety"},{"id":"2603.07452","title":"Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs","created":"2026-03-08","cited_by_count":0,"area":"safety"},{"id":"2605.18879","title":"ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models","created":"2026-05-16","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":"2610.00663","title":"Backdoor Containment via Expert Quarantine and Shutdown in LLMs","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.00685","title":"Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}