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

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding
Sep 12, 2026Wissam Ghantous, Alexander V. MantzarisLLM Security
University of Central Florida Orlando, Florida, USA
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
Sep 10, 2026Syed Ghazanfar Abbas, Dongyan XuLLM Security Language Model Auditing
Purdue University
HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving
Sep 8, 2026Han JinLLM Serving Adversarial Attacks on LLMs
Independent Researcher
The Implications of Linguistic Illegibility for LLM Security
Sep 2, 2026James MickensLLM Security
Harvard University
Capability-Gated Language Models: Security Composes, Utility Does Not
Aug 31, 2026Patrikas Vanagas, Augustas Mačijauskas, Laurynas LopataLanguage Model Safety Evaluation LLM Security
BPTI Vilnius, Lithuania · Independent Researcher Vilnius, Lithuania · askEarth AG Zürich, Switzerland
Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text
Aug 31, 2026Minkyung Cho, Jihyo Kim, SeungWoo Song +4Social Bias in Language Models LLM Security
KAIST · KAIST InnoCORE PRISM-AI Center · Department of Artificial Intelligence, Dankook University
Interpreting and Steering for Safe and Correct Code Generation
Aug 30, 2026Hao Yan, Ziyu YaoMechanistic Interpretability LLM Security
Department of Computer Science George Mason University, Fairfax, VA
Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?
Aug 30, 2026Alberto CetoliLanguage Model Generation Evaluation Language Model Self-Assessment
Cleo
Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code
Aug 28, 2026Animesh ShawLLM Security LLM Code Generation
Backdoor Decontamination Dynamics in LLM Agents
Aug 11, 2026Gabriel Huang, Abhay Puri, Léo Boisvert +4LLM Backdoor Attacks Backdoor Defense in LLMs
ServiceNow Research · Mila – Quebec AI Institute · Polytechnique Montréal +3
On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models
Aug 11, 2026Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan AnsariLLM Agent Security LLM Security
Florida International University, Miami, Florida, USA · Middle Tennessee State University, Murfreesboro, Tennessee, USA · New Jersey Institute of Technology, Newark, NJ, USA
Stealing Reasoning Traces from Proprietary LLM APIs
Aug 10, 2026Alexander Panfilov, David Schmotz, Ilia Shumailov +5Model Extraction Attacks Adversarial Attacks
MATS Research · ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems +4
Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
Aug 10, 2026Hongli Shen, Shaopeng Fu, Qinbo Zhang +2Adversarial Training Adversarial Attacks on LLMs
1King Abdullah University of Science and Technology · 2Stony Brook University
Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference
Aug 10, 2026Tejasvi C. AddagadaKV Caching KV-Cache Management
The Anatomy of a Prompt Injection: A Component Model for Structured Analysis
Aug 7, 2026Jeremy McHughLLM Security Prompt Injection Attacks
Preamble, Inc.
Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
Aug 7, 2026Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj +4AI Risk Management LLM Security
Department of Administrative Sciences, Metropolitan College, Boston University, Boston, MA 02215, USA · Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje 1000, North Macedonia · Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA
LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
Aug 7, 2026Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1LLM Backdoor Attacks Backdoor Detection
Michigan Technological University · Miami University · Lehigh University
Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models
Aug 7, 2026Zhuoheng Huang, Mukesh SinghLLM Auditing Sparse Mixture-of-Experts
Independent Researcher
Hardware Design and Security in the Era of Chiplets and LLMs
Aug 5, 2026Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz +1Electronic Design Automation Cybersecurity
NYU Abu Dhabi · Texas A&M University · NYU Tandon School of Engineering
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Aug 5, 2026Yuxuan Huang, Xingyu Zeng, Tianhang Zheng +1LLM Safety Alignment LLM Security
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Shenzhen University of Advanced Technology +1
An Inline Control Architecture for Language Models in Intelligent Transportation Systems
Aug 4, 2026Narendra Kumar Dewangan, Mounira MsahliLLM Guardrails Adversarial Attacks on LLMs
LTCI, Département Informatique et Réseaux, Télécom Paris, Institut Polytechnique de Paris, France
A Security-Oriented Lifecycle Model for Large Language Model Systems
Aug 4, 2026Eleftherios Batzolis, George Drosatos, Vassilis Katsouros +1AI Assurance LLM Security
Department of Informatics, Democritus University of Thrace, Kavala, Greece · Institute for Language and Speech Processing, Athena Research Center, Xanthi, Greece
AI Security Leaderboard: Methodology, Results and Minimal Standard
Aug 4, 2026Jasper Timm, Lukas Struppek, Ziwei Xu +12LLM Safety Benchmarks Cybersecurity
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels
Aug 4, 2026Yongwan Jo, Jinyoung Park, Euihyun Lee +1Privacy Leakage in Language Models LLM Security
Department of Computer Science Yonsei University
LaCache: Robust Semantic Caching for LLM Serving
Aug 3, 2026Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1LLM Serving LLM Security
Stony Brook University
DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial
Aug 2, 2026Abay Zhurekbay, Tao Liu, Fan LiKnowledge Conflicts in Language Models RAG Poisoning Attacks
Lawrence Technological University
TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement
Jul 30, 2026Cheng WeiBackdoor Attacks Backdoor Attacks in Federated Learning
Honor Device Co., Ltd., Shenzhen, China
Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?
Jul 28, 2026Farooq ShaikhAutomated Program Repair LLM Prompting
Dynatrace Research, Linz, Austria
Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
Jul 28, 2026Yongyi Cui, Yue Li, Tianbao Jiang +1Language Model Fingerprinting LLM Security
East China Normal University
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
Jul 28, 2026Yu Yan, Jiahao Chen, Siqi Lu +6LLM Alignment Adversarial Attacks on LLMs
College of Computer Science and Technology, Zhejiang University · Henan Key Laboratory of Network Cryptography Technology, Information Engineering University · State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences

Sep 12, 2026, cs.CRJ/K move · Enter open · S save

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding

Wissam Ghantous, Alexander V. Mantzaris

University of Central Florida Orlando, Florida, USA

LLM Security

Open paper AskPDF arXiv

Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank information across contexts - a methodology we formalize as Contextual Autoregressive Rank Transcoding Steganography (CARTS). While the Calgacus construction of Norelli et al. demonstrated this phenomenon experimentally, no formal security analysis existed. This paper provides the first rigorous treatment of CARTS. We show its exact correctness under deterministic model assumptions, introduce a rank-coordinate representation in which keys act as bijections on rank-vector space, define relevant security notions and the computational problems naturally associated with the construction - context search, key collisions, message equivocation, and non-commutativity of the encoding maps - and study the theoretical relationships between them, including the characterization of message equivocation in terms of context search, and the tension between key collisions and message equivocation. An empirical study on Llama 3 8B confirms exact recovery of the original payload in all tested cases, finds no key collisions under random key generation, establishes that a hand-crafted collision is local rather than global, and finds no commuting key pairs - suggesting resistance to the attack vectors studied. This work opens a formally grounded research agenda for the constructive use of language models in cryptography and privacy-preserving communication.

Momentum

Related topics

Latest papers 200