LLM Security

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 127% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 200

All topics

LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
Oct 8, 2026Luman Zhao, Minghui Xu, Yue Zhang +1LLM Security Prompt Injection Defense
Shandong University, Shandong Academy of Artificial Intelligence
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Oct 7, 2026Hui Zhang, Yachao Yuan, Jiayun Wang +3LLM Security LLM Safety
North China Electric Power University · Southeast University · Soochow University +1
Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and Mitigation
Oct 7, 2026Teng-Ruei ChenPrivacy Leakage in Language Models LLM Routing
Krixvon, Taipei 100, Taiwan
Secure Speculative Decoding for Large Language Models
Oct 6, 2026Yichi Zhang, Zhiqi Wang, Neil Gong +1Adversarial Attacks on LLMs Speculative Decoding
The Pennsylvania State University · Duke University
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Oct 6, 2026Yibo Zhang, Tianrong Guan, Liang Lin +3LLM Backdoor Attacks Backdoor Attacks
Queen Mary University of London, UK · Squirrel AI Learning, USA
Does On-Policy Distillation for Safety Pose Backdoor Risks?
Oct 6, 2026Jian Luo, Kehan Qi, Qingqiao Hu +5LLM Backdoor Attacks LLM Security
Stony Brook University · Amazon
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Oct 5, 2026Wonjun Lee, Kyungsik Yang, Gaeun Ji +5Adversarial Attacks on LLMs LLM Security
UNC Chapel Hill · Kyung Hee University · AIM Intelligence +1
Backdooring Sparse Autoencoders
Oct 5, 2026Enrico Ahlers, Daniel Passon, Tobias Kiecker +2LLM Backdoor Attacks Adversarial Attacks
Humboldt-Universität zu Berlin Berlin, Germany
Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs
Oct 4, 2026Noor Munir, Francesco Quinzan, Stephen RobertsLLM Security Indirect Prompt Injection
Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, UK
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Oct 4, 2026Shang Wang, Tianqing Zhu, Huajie Chen +3LLM Backdoor Attacks Model Extraction Attacks
School of Computer Science, University of Technology Sydney, Sydney, Australia · Faculty of Data Science, City University of Macau, Macau, China
The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching
Oct 1, 2026Alessandro Pegoraro, Daryan Merx, Phillip Rieger +1LLM Agent Security Privacy Leakage in Language Models
Technical University of Darmstadt · Graz University of Technology
Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing
Sep 30, 2026Kemou Li, Qizhou Wang, Yue Wang +6LLM Security LLM Safety
State Key Laboratory of Internet of Things for Smart City, University of Macau · RIKEN Center for Advanced Intelligence Project · The University of Melbourne +5
When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models
Sep 30, 2026Pakhapoom Sarapat, Saksorn Ruangtanusak, Kunat Pipatanakul +1Large Language Model-Based Role-Play Simulation LLM Security
SCB DataX · Nanyang Technological University
Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Sep 30, 2026Julian Schulz, Lukas Fülle, Rieke FruengelLLM Security Implicit Reasoning in Language Models
Meridian Cambridge · SAIGE
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Sep 30, 2026Fahao Chen, Linkang Du, Jinhao Zhou +2LLM Inference Privacy Leakage in Language Models
Shandong University China · Xi’an Jiaotong University China · Waseda University Japan
Security-Enhanced Seed-Based Weight Quantization for Large Language Models
Sep 29, 2026Qiuyu Ren, Sudipta Paria, Aritra Dasgupta +1LLM Quantization LLM Compression
Department of Electrical and Computer Engineering (ECE) University of Florida Gainesville, FL 32611, USA
Breaking the Illusion of Review Reliability under Static Evaluation: SCOPE Fuzzing for LLM-based Scientific Reviewers
Sep 29, 2026Zhuo Chen, Hao Zeng, Jiawei Liu +6LLM Evaluation Adversarial Attacks on LLMs
Wuhan University · East China Normal University
Distillation Defenses Easily Break After Reinforcement Learning
Sep 28, 2026Shidan Javaheri, Alexander Panfilov, Oliver Britton +2LLM Security Language Model Distillation
University of Oxford · ELLIS Institute Tübingen & MPI for Intelligent Systems
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Sep 28, 2026Zihan Zhang, Shuangjie Yao, Zesen Liu +8LLM Security Data Poisoning Attacks
The Hong Kong University of Science and Technology · Tsinghua University
The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning
Sep 27, 2026Sae Furukawa, Alina OpreaSupervised Fine-Tuning Privacy Leakage in Language Models
Khoury College of Computer Sciences, Northeastern University
On the security and privacy of LLMs in Mobility
Sep 22, 2026Mauro Conti, Lorenzo Perinello, Umberto SalviatiIntelligent Transportation Systems LLM Security
University of Padova Italy · Fondazione Bruno Kessler Italy
SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy Evaluation
Sep 21, 2026Fatih Deniz, Yazan Boshmaf, Issa KhalilLLM Safety Benchmarks LLM Evaluation
Qatar Computing Research Institute (QCRI), HBKU, Doha, Qatar
Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
Sep 17, 2026Sarah Radway, Andrew Cheng, Vijay Janapa Reddi +1Language Model Fingerprinting Software Security
Harvard University
ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers
Sep 17, 2026Hyeongjun Choi, Wonyoung Jung, Haehoon Seo +1Adversarial Attacks on LLMs LLM Security
78ResearchLab Seoul, South Korea
For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances
Sep 16, 2026Alexander Shirnin, Aleksey KudelyaDeception in Language Models LLM Security
Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs
Sep 15, 2026Kisu Yang, Yoonna Jang, Heuiseok LimAdversarial Attacks on LLMs LLM Security
1VAIV Company · 2Hanwha Aerospace · 3Korea University
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Sep 14, 2026Keertana Chidambaram, Andrew Ilyas, Vasilis SyrgkanisLLM Security Prompt Injection Attacks on AI Agents
Stanford University · CMU
Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
Sep 14, 2026Danny Wood, James StringerLLM Security
Fuzzy Labs
Overflip: Repetition-Induced Label Flips in Guardrail Models
Sep 14, 2026Xu He, Chih-Hsuan Lin, Hung-Mao Chen +3LLM Guardrails Adversarial Attacks on LLMs
1George Mason University · 2Virginia Tech · 3Missouri University of Science and Technology +1
What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code
Sep 14, 2026Cristina Improta, Pietro Liguori, Domenico CotroneoLLM Security Code Generation Evaluation
University of Naples Federico II, Naples, Italy · University of North Carolina at Charlotte, Charlotte, NC, USA

Oct 8, 2026, cs.CRJ/K move · Enter open · S save

LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense

Luman Zhao, Minghui Xu, Yue Zhang, Yijun Yang

Shandong University, Shandong Academy of Artificial Intelligence

LLM Security Prompt Injection Defense Prompt Injection Attacks on LLMs

Open paper AskPDF arXiv

Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent. Existing defenses remain limited by model fine-tuning requirements, vulnerability to adaptive attacks, or reliance on brittle handcrafted prompts. We argue that a fundamental source of this vulnerability is the lack of an explicit representation of trust provenance. To address this, we introduce Learnable Trust-Boundary Delimiters (LTBD), a lightweight defense that explicitly encodes trust boundaries in the input while keeping the LLM parameters unchanged. LTBD uses a small number of learnable delimiters to distinguish trusted user instructions from untrusted external data, enabling the model to better respect the intended trust hierarchy. Experimental results show that LTBD substantially outperforms inference-time defenses and performs competitively with training-based approaches, while preserving benign-task utility and introducing negligible inference overhead. In particular, LTBD achieves 0.00% ASR on AlpacaFarm and only 0.11-0.19% ASR on TaskTracker. LTBD also remains effective under adaptive attacks, where adversaries have full knowledge of the defense and explicitly attempt to bypass it.

Momentum

Related topics

Latest papers 200