Large Language Model Safety

Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

27 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Period ending 2026-09-14

12 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Inside this field

Focused directions

855 papers

Latest in Large Language Model Safety

Browse all topics →
CardsList

  1. Social Pressure Breaks Majority Voting in LLM Safety Panels

    Aug 5, 2026Yibo Hu, Jiaming QuLarge Language Model SafetyReview

  2. DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning

    Aug 5, 2026Junbo Zhang, Qianli Zhou, Xinyang Deng +1Large Language Model SafetyLarge Language Model Fine-Tuning

  3. Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks

    Aug 4, 2026Atri Vivek Sharma, Brian Formento, Alessio LomuscioLarge Language Model HallucinationLanguage Model Evasion Attacks

  4. LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards

    Aug 4, 2026Zhinan Liu, Jie Li, Mingyu Kang +1Large Language Model SafetyGuard

  5. An Inline Control Architecture for Language Models in Intelligent Transportation Systems

    Aug 4, 2026Narendra Kumar Dewangan, Mounira MsahliV2XLarge Language Model Safety

  6. Risky Business: Measuring The Faithfulness-Safety Tension

    Aug 4, 2026Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser +3Large Language Model SafetyFaithfulness

  7. A Security-Oriented Lifecycle Model for Large Language Model Systems

    Aug 4, 2026Eleftherios Batzolis, George Drosatos, Vassilis Katsouros +1Large Language Model SafetySecurity

  8. AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

    Aug 4, 2026Shihao Weng, Yang Feng, Xiaofei Xie +1Indirect Prompt InjectionLanguage Model Evasion Attacks

  9. When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

    Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4RefusalsGuard

  10. Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation

    Aug 4, 2026Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi +1Adversarial EvaluationRole-Playing Agents

  11. SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels

    Aug 4, 2026Yongwan Jo, Jinyoung Park, Euihyun Lee +1Language Model Evasion AttacksSide-Channel Analysis

  12. Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech

    Aug 3, 2026Shadab Bin Habib, A K M Ferdous Reza Habib, Subarno Neel +1Large Language Model SafetyBangla

  13. Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions

    Aug 3, 2026Nicole Mitchell, Dhruv Agarwal, Maty Bohacek +2Human-Ai InteractionLongitudinal

  14. EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers

    Aug 3, 2026Junyeong Park, Jieun Han, Haneul Yoo +3Large Language Model SafetyClassrooms

  15. Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

    Aug 3, 2026Jia-Chen Zhang, Ze-Yu Zhang, Kai-Wei ZhangIndirect Prompt InjectionAdversarial Evaluation

  16. Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models

    Aug 3, 2026Junxiang You, Junkai Chen, Yuhao He +3Large Language Model UnlearningMachine Unlearning

  17. EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming

    Aug 3, 2026Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne +4Vulnerability Detection & RepairLarge Language Model Safety

  18. LaCache: Robust Semantic Caching for LLM Serving

    Aug 3, 2026Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1CacheLanguage Model Evasion Attacks

  19. Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch

    Aug 3, 2026Shuyang Xie, Shuxiao Xie, Feng Zhu +2Raw Judge OutputsBug

  20. MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model

    Aug 3, 2026Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi AtaniCybersecurityLarge Language Model Safety

  21. A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

    Aug 3, 2026Shu Quan, Tianfang Hao, Sitong Fang +8Large Language Model SafetyToxicity

  22. DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

    Aug 2, 2026Abay Zhurekbay, Tao Liu, Fan LiRetrieval-Augmented Generation SystemsLanguage Model Evasion Attacks

  23. ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification

    Aug 2, 2026Wajdi Zaghouani, Md. Rafiul Biswas, Kholoud Khalil Aldous +1Arabic Natural Language ProcessingArabic

  24. Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation

    Aug 2, 2026Francis Luis Santos Vargas, Rodrigo Brandão Mansilha, Diego KreutzLarge Language Model SafetyCode Generation

  25. Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity

    Aug 1, 2026Yongxi Zhou, Junwei Yao, Yuanzhe Liu +4Large Language Model SafetySafety

  26. AdvPlan-Bench: Adversarial Evaluation of Structured Plan-Generation Agents

    Aug 1, 2026Alina Kapanova, Arun Kanhai, Natan Vidra +1Adversarial Evaluation

  27. Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

    Aug 1, 2026Faisal Haque Bappy, Tahrim Hossain, Tarannum Shaila Zaman +3Language Model Evasion AttacksVulnerability Detection & Repair

  28. OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

    Aug 1, 2026Yunhao Chen, Xin Wang, Yixu Wang +6Agentic EvaluationsRed-Teaming

  29. From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness

    Aug 1, 2026Jonas Thurner, Nadine Jost, Stefan Albert Horstmann +4CybersecurityLarge Language Model Safety

  30. Auditable Release Control for Pedagogical Leakage in LLM Tutors

    Aug 1, 2026Nizam KadirLarge Language Model SafetyData Leakage

  31. Towards General Language-Conditioned Latent Safety Filters

    Jul 31, 2026Ihab Tabbara, Yuxuan Yang, Hussein SibaiSafety FiltersVision-Language-Action Models

  32. ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation

    Jul 31, 2026Gaetano Perrone, Simon Pietro RomanoMachine-Generated Text DetectionBenchmarking Large Language Models

  33. Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

    Jul 31, 2026Minghui Pan, Jiayuxuan Yang, Yuanyuan Yuan +2Large Language Model SafetyInference-Time Defense

  34. Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization

    Jul 31, 2026Tyler Ashoff, Jordan RoduArtificial Intelligence AlignmentMultimodal Alignment

  35. Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

    Jul 31, 2026Weiyi He, Yuping Lin, Jiliang Tang +1Language Model Evasion AttacksAdversarial Transferability

  36. TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

    Jul 30, 2026Chengshuai Zhao, Pingchuan Ma, Dawei Li +4Language Model Evasion AttacksLarge Language Model Unlearning

  37. AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

    Jul 30, 2026Xiangning Lin, Shenzhe Zhu, Shu Yang +23Artificial Intelligence GovernanceArtificial Intelligence Systems

  38. Cybersecurity Detection Classification with Reasoning-enabled Language Models

    Jul 30, 2026Amol Khanna, Manu Nandan, Cristian Viorel Popa +10Large Language Model SafetyArtificial Intelligence Detection

  39. Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

    Jul 30, 2026I. Kennedy, T. KennedyLarge Language Model SafetyUntrusted Input

  40. Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

    Jul 30, 2026Pingyu Wu, Lingyao Zhu, Weiming Zhang +1Large Language Model SafetySafeguard

  41. On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

    Jul 29, 2026Yongjian Guo, Wanlun Ma, Lingyu Shen +2Safety AlignmentLarge Language Model Safety

  42. Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions

    Jul 29, 2026Shi Lin, Peng Qian, Dinghao Liu +5Large Language Model SafetySafety

  43. FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs

    Jul 29, 2026Yifan Zhang, Xinkui Zhao, Sai Liu +3AuthorizationRuntime Enforcement

  44. Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis

    Jul 29, 2026Jiachen Qian, Junyu LiLarge Audio Language ModelsJailbreak Evaluations

  45. SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

    Jul 29, 2026Yi Cui, Zilin Wang, Yijie Xu +5Safety EvaluationHazard

  46. Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?

    Jul 28, 2026Farooq ShaikhKubernetesRemediation

  47. GPT-Red: Automated Red Teaming via Self-Play at Scale

    Jul 28, 2026Eric Wallace, Christopher A. Choquette-Choo, Nikhil Kandpal +15Red-TeamingLanguage Model Evasion Attacks

  48. Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

    Jul 28, 2026Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal +1Model ActivationsLarge Language Model Safety

  49. Shieldstral

    Jul 28, 2026Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273Content ModerationLarge Language Model Safety

  50. Hybrid Analysis for Secure MCP Tool Use in LLM Agents

    Jul 28, 2026Ping He, Yuexiang Xie, Yaliang Li +1Large Language Model SafetyDefense Strategies

  51. Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks

    Jul 28, 2026Yu Yan, Jiahao Chen, Siqi Lu +6Language Model Evasion AttacksLarge Language Model Decision-Making

  52. SecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code

    Jul 28, 2026Narayanaswami Natraj Bharadwaj, Dhivya ChandramouleeswaranVulnerability Detection & RepairCode Quality

  53. Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards

    Jul 27, 2026Xi Li, Shu Zhao, Xiaohan Zou +6Large Language Model SafetyMulti-Modal Large Language Models

  54. Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

    Jul 27, 2026Xinnuo Xu, Anja Thieme, Daniela Massiceti +6ToxicityText-To-Image

  55. Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls

    Jul 27, 2026Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin +4Conformal Risk ControlLarge Language Model Safety

  56. EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability

    Jul 27, 2026Andrea Ponte, Daniel Gibert, Matous Kozak +5Malware DetectionSecurity Analysis

  57. Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders

    Jul 26, 2026Ge Zhang, Jingru Cheng, Huiyuan ChenRerankingLanguage Model Evasion Attacks

  58. The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting

    Jul 26, 2026Ishpuneet Singh, Shreyas Mahajan, Gurjot Singh +1Large Language Model SafetySecurity

  59. Do LLMs Know Their Vulnerable Scenarios?

    Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Large Language Model SafetyVulnerable Code

  60. Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

    Jul 25, 2026Lixun Ma, Ruolong Ma, Bei Wang +4Large Language Model SafetyVulnerable Code