{"total":47,"rows":[{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141,"area":"safety"},{"id":"2308.00113","title":"Three Bricks to Consolidate Watermarks for Large Language Models","created":"2023-07-26","cited_by_count":84,"area":"safety"},{"id":"2403.13485","title":"An Entropy-based Text Watermarking Detection Method","created":"2024-03-20","cited_by_count":75,"area":"safety"},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"area":"safety"},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28,"area":"safety"},{"id":"2404.15639","title":"CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code","created":"2024-04-24","cited_by_count":24,"area":"safety"},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24,"area":"safety"},{"id":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"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":"2506.05502","title":"StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models","created":"2025-06-05","cited_by_count":12,"area":"safety"},{"id":"2503.21730","title":"Effective Skill Unlearning through Intervention and Abstention","created":"2025-03-27","cited_by_count":9,"area":"safety"},{"id":"2503.21598","title":"Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing","created":"2025-03-27","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":"2509.13755","title":"Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning","created":"2025-09-17","cited_by_count":7,"area":"safety"},{"id":"2402.07518","title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","created":"2024-02-12","cited_by_count":6,"area":"safety"},{"id":"2505.14112","title":"Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2602.06754","title":"A Unified Framework for LLM Watermarks","created":"2026-02-06","cited_by_count":5,"area":"safety"},{"id":"2501.12174","title":"BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks","created":"2025-01-21","cited_by_count":3,"area":"safety"},{"id":"2510.02342","title":"CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models","created":"2025-09-27","cited_by_count":3,"area":"safety"},{"id":"2601.22246","title":"MirrorMark: Generalizable Mirrored Sampling for Multi-bit LLM Watermarking","created":"2026-01-29","cited_by_count":3,"area":"safety"},{"id":"2512.16904","title":"How Good is Post-Hoc Watermarking With Language Model Rephrasing?","created":"2025-12-18","cited_by_count":2,"area":"safety"},{"id":"2602.06911","title":"TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering","created":"2026-02-06","cited_by_count":2,"area":"safety"},{"id":"2604.22438","title":"SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking","created":"2026-04-24","cited_by_count":2,"area":"safety"},{"id":"2408.01354","title":"MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code","created":"2024-08-02","cited_by_count":1,"area":"safety"},{"id":"2508.11925","title":"Optimizing Token Choice for Code Watermarking: An RL Approach","created":"2025-08-16","cited_by_count":1,"area":"safety"},{"id":"2510.01644","title":"Machine Learning for Detection and Analysis of Novel LLM Jailbreaks","created":"2025-10-02","cited_by_count":1,"area":"safety"},{"id":"2602.02509","title":"CodeGuard: Improving LLM Guardrails in CS Education","created":"2026-01-22","cited_by_count":1,"area":"safety"},{"id":"2605.11653","title":"Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark","created":"2026-05-12","cited_by_count":1,"area":"safety"},{"id":"2502.02068","title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","created":"2025-02-04","cited_by_count":0,"area":"safety"},{"id":"2505.18672","title":"Concept Concentration for Faithful Representation Intervention","created":"2025-05-24","cited_by_count":0,"area":"safety"},{"id":"2512.03089","title":"Password-Activated Shutdown Protocols for Misaligned Frontier Agents","created":"2025-11-29","cited_by_count":0,"area":"safety"},{"id":"2512.04044","title":"MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2601.11629","title":"Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs","created":"2026-01-14","cited_by_count":0,"area":"safety"},{"id":"2604.27426","title":"Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors","created":"2026-04-30","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":"2606.11817","title":"Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2606.18430","title":"Signature filtering: a lightweight enhancement for statistical watermark detection in large language models","created":"2026-06-16","cited_by_count":0,"area":"safety"},{"id":"2606.19235","title":"CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2606.28962","title":"FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks","created":"2026-06-27","cited_by_count":0,"area":"safety"},{"id":"2607.02072","title":"kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail","created":"2026-07-02","cited_by_count":0,"area":"safety"},{"id":"2607.20852","title":"Code Monitor Red Teaming for Public-Test-Passing Code","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2608.30703","title":"SingProbe Technical Report","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.09604","title":"Watermarks Without Verification: AI Text Watermarking After the EU AI Act","created":"2026-09-09","cited_by_count":0,"area":"safety"},{"id":"2609.20129","title":"Local Sparsity Enables Unsupervised LLM Safety Detection","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.35913","title":"UNBIND: UNlearning By INference-time Directional Steering for Code LLMs","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2610.00348","title":"Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.02817","title":"RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models","created":"2026-10-02","cited_by_count":0,"area":"safety"}],"next_cursor":null}