{"total":85,"rows":[{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367,"area":"safety"},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"area":"safety"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"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":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60,"area":"safety"},{"id":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52,"area":"safety"},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2502.07218","title":"LLM Unlearning via Neural Activation Redirection","created":"2025-02-11","cited_by_count":41,"area":"safety"},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41,"area":"safety"},{"id":"2406.15481","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","created":"2024-06-17","cited_by_count":34,"area":"safety"},{"id":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30,"area":"safety"},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2501.07238","title":"Lessons From Red Teaming 100 Generative AI Products","created":"2025-01-13","cited_by_count":23,"area":"safety"},{"id":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"area":"safety"},{"id":"2410.16531","title":"Bayesian scaling laws for in-context learning","created":"2024-10-21","cited_by_count":19,"area":"safety"},{"id":"2205.14055","title":"A Blessing of Dimensionality in Membership Inference through Regularization","created":"2022-05-27","cited_by_count":18,"area":"safety"},{"id":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17,"area":"safety"},{"id":"2603.24511","title":"Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs","created":"2026-03-25","cited_by_count":17,"area":"safety"},{"id":"2502.19726","title":"Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training","created":"2025-02-27","cited_by_count":15,"area":"safety"},{"id":"2509.24384","title":"HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment","created":"2025-09-29","cited_by_count":15,"area":"safety"},{"id":"2502.05911","title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","created":"2025-02-09","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":"2604.18519","title":"LLM Safety From Within: Detecting Harmful Content with Internal Representations","created":"2026-04-20","cited_by_count":11,"area":"safety"},{"id":"2308.13449","title":"The Poison of Alignment","created":"2023-08-25","cited_by_count":10,"area":"safety"},{"id":"2403.14988","title":"Risk and Response in Large Language Models: Evaluating Key Threat Categories","created":"2024-03-22","cited_by_count":10,"area":"safety"},{"id":"2408.11851","title":"SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming","created":"2024-08-14","cited_by_count":10,"area":"safety"},{"id":"2503.04693","title":"UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets","created":"2025-03-06","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":"2505.19773","title":"What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs","created":"2025-05-26","cited_by_count":8,"area":"safety"},{"id":"2411.19563","title":"Ensemble Watermarks for Large Language Models","created":"2024-11-29","cited_by_count":7,"area":"safety"},{"id":"2505.23270","title":"Does Machine Unlearning Truly Remove Knowledge?","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"id":"2501.13115","title":"Dagger Behind Smile: Fool LLMs with a Happy Ending Story","created":"2025-01-19","cited_by_count":6,"area":"safety"},{"id":"2505.15178","title":"A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning","created":"2025-05-21","cited_by_count":6,"area":"safety"},{"id":"2507.05068","title":"ICAS: Detecting Training Data from Autoregressive Image Generative Models","created":"2025-07-07","cited_by_count":6,"area":"safety"},{"id":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2406.12800","title":"Supporting Human Raters with the Detection of Harmful Content using Large Language Models","created":"2024-06-18","cited_by_count":5,"area":"safety"},{"id":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","cited_by_count":5,"area":"safety"},{"id":"2604.15022","title":"Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization","created":"2026-04-16","cited_by_count":5,"area":"safety"},{"id":"2403.09832","title":"Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks","created":"2024-03-14","cited_by_count":4,"area":"safety"},{"id":"2405.08400","title":"Stylometric Watermarks for Large Language Models","created":"2024-05-14","cited_by_count":4,"area":"safety"},{"id":"2407.16951","title":"Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation","created":"2024-07-24","cited_by_count":4,"area":"safety"},{"id":"2410.04190","title":"Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2502.16174","title":"Efficient LLM Moderation with Multi-Layer Latent Prototypes","created":"2025-02-22","cited_by_count":4,"area":"safety"},{"id":"2506.17125","title":"Large Language Model Unlearning for Source Code","created":"2025-06-20","cited_by_count":4,"area":"safety"},{"id":"2509.14594","title":"SynBench: A Benchmark for Differentially Private Text Generation","created":"2025-09-18","cited_by_count":4,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2502.06567","title":"Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study","created":"2025-02-10","cited_by_count":3,"area":"safety"},{"id":"2503.07697","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"safety"},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","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":"2604.12820","title":"RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair","created":"2026-04-14","cited_by_count":3,"area":"safety"},{"id":"2410.13236","title":"SPIN: Self-Supervised Prompt INjection","created":"2024-10-17","cited_by_count":2,"area":"safety"},{"id":"2501.10800","title":"Jailbreaking Large Language Models in Infinitely Many Ways","created":"2025-01-18","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":"2502.18518","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2502.19883","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","created":"2025-02-27","cited_by_count":2,"area":"safety"},{"id":"2508.06467","title":"LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2511.13788","title":"Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments","created":"2025-11-16","cited_by_count":2,"area":"safety"},{"id":"2601.22589","title":"FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery","created":"2026-01-30","cited_by_count":2,"area":"safety"},{"id":"2603.11149","title":"Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2604.12686","title":"BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning","created":"2026-04-14","cited_by_count":2,"area":"safety"},{"id":"2605.31293","title":"Divergence Decoding: Inference-Time Unlearning via Auxiliary Models","created":"2026-05-29","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":"2405.04756","title":"Red-Teaming for Inducing Societal Bias in Large Language Models","created":"2024-05-08","cited_by_count":1,"area":"safety"},{"id":"2506.16575","title":"Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System","created":"2025-06-19","cited_by_count":1,"area":"safety"},{"id":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2511.08367","title":"Why Does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs","created":"2025-11-11","cited_by_count":1,"area":"safety"},{"id":"2512.15335","title":"Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference","created":"2025-12-17","cited_by_count":1,"area":"safety"},{"id":"2512.21110","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2603.14484","title":"Unlearning-based sliding window for continual learning under concept drift","created":"2026-03-15","cited_by_count":1,"area":"safety"},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2606.11409","title":"Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models","created":"2026-06-09","cited_by_count":1,"area":"safety"},{"id":"2606.25476","title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2407.13744","title":"LLMs as Function Approximators: Terminology, Taxonomy, and Questions for Evaluation","created":"2024-07-18","cited_by_count":0,"area":"safety"},{"id":"2512.21395","title":"A Reinforcement Learning Approach to Synthetic Data Generation","created":"2025-12-24","cited_by_count":0,"area":"safety"},{"id":"2605.01047","title":"LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.27083","title":"On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2608.29943","title":"On the Recoverability of Private Information Unlearning in Large Language Models","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.32288","title":"A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2610.08540","title":"Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements","created":"2026-10-06","cited_by_count":0,"area":"safety"}],"next_cursor":null}