{"total":50,"rows":[{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41,"area":"safety"},{"id":"2603.06594","title":"A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness","created":"2026-02-04","cited_by_count":20,"area":"safety"},{"id":"2509.21057","title":"PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints","created":"2025-09-25","cited_by_count":16,"area":"safety"},{"id":"2509.26238","title":"Beyond Linear Probes: Dynamic Safety Monitoring for Language Models","created":"2025-09-30","cited_by_count":16,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2510.09694","title":"Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection","created":"2025-10-09","cited_by_count":9,"area":"safety"},{"id":"2512.06674","title":"RunawayEvil: Jailbreaking the Image-to-Video Generative Models","created":"2025-12-07","cited_by_count":8,"area":"safety"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","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":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2506.17299","title":"Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem","created":"2025-06-17","cited_by_count":4,"area":"safety"},{"id":"2508.05557","title":"MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media","created":"2025-08-07","cited_by_count":4,"area":"safety"},{"id":"2605.06605","title":"How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation","created":"2026-05-07","cited_by_count":4,"area":"safety"},{"id":"2601.08490","title":"BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2601.19448","title":"From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense","created":"2026-01-27","cited_by_count":3,"area":"safety"},{"id":"2605.08778","title":"Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking","created":"2026-05-09","cited_by_count":3,"area":"safety"},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","cited_by_count":2,"area":"safety"},{"id":"2509.25843","title":"ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2602.06440","title":"TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2602.12318","title":"Abstractive Red-Teaming of Language Model Character","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2603.13847","title":"Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs","created":"2026-03-14","cited_by_count":1,"area":"safety"},{"id":"2604.25921","title":"One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2605.00553","title":"Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"id":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","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":"2606.19887","title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2601.13359","title":"Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.16752","title":"The Vulnerability of LLM Rankers to Prompt Injection Attacks","created":"2026-02-18","cited_by_count":0,"area":"safety"},{"id":"2604.12232","title":"TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs","created":"2026-04-14","cited_by_count":0,"area":"safety"},{"id":"2605.17658","title":"When a Zero-Shooter Cheats: Improving Age Estimation via Activation Steering","created":"2026-05-17","cited_by_count":0,"area":"safety"},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2607.09804","title":"Trivial Prompt Reframing Bypasses Safety Guardrails in Google\\'s MedGemma-4B","created":"2026-07-09","cited_by_count":0,"area":"safety"},{"id":"2607.20462","title":"Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2608.00068","title":"SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining","created":"2026-07-29","cited_by_count":0,"area":"safety"},{"id":"2608.10171","title":"Generating Attacks for LLMs with GFlowNets","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2608.11348","title":"An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs","created":"2026-08-11","cited_by_count":0,"area":"safety"},{"id":"2608.25490","title":"MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2609.16229","title":"Test-Time Unlearning via Sparse Autoencoder","created":"2026-09-14","cited_by_count":0,"area":"safety"},{"id":"2609.39866","title":"Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.02302","title":"Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.05453","title":"The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models","created":"2026-10-04","cited_by_count":0,"area":"safety"},{"id":"2610.06049","title":"Backdooring Sparse Autoencoders","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.07532","title":"Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.09033","title":"Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs","created":"2026-10-06","cited_by_count":0,"area":"safety"},{"id":"2610.12106","title":"Could LLM Watermark Detection be Public?","created":"2026-10-08","cited_by_count":0,"area":"safety"}],"next_cursor":null}