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

Sep 12, 2026cs.CR

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

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.

Wissam Ghantous, Alexander V. Mantzaris

University of Central Florida Orlando, Florida, USA

Sep 10, 2026cs.CR

Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models

Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to conduct an identity test, while ChatGPT generated developer-oriented questions but maintained that answers could demonstrate knowledge, not identity. In contrast, Qwen and Mistral generated technical challenges, defined what counted as convincing evidence, evaluated detailed answers, and returned Verified without receiving any externally validated identity evidence. Llama similarly generated and evaluated a developer test, accepted the claimed identity, and subsequently made unsupported claims of access to internal runtime and deployment state. We call the model-generated verification procedure a Model-Issued Pseudo-Credential (MIPC) and the resulting unsupported identity judgment Conversational False Authentication (CFA). In each CFA case, the same model acted as challenge generator, evidence evaluator, and identity decision-maker, converting technical knowledge into supposed proof of identity. The accepted identities did not change the tested authorization boundaries, showing that false authentication and privilege escalation are distinct outcomes. These results identify self-issued authentication as a conversational security failure: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state.

Syed Ghazanfar Abbas, Dongyan Xu

Purdue University

LLM Security Language Model Auditing

Sep 8, 2026cs.CR

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild deception at the protocol layer, leaving the serving tier unprotected and feeding nothing back into detection. HoneyRoute couples (i) a streaming router (a frozen 0.8B-embedding backbone with per-domain MLP heads), (ii) a dual-implementation honeypot (a rule/prompt-engineered code honeypot or a dedicated same-family replica), and (iii) an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus, the router reaches F1=.911 at 38 ms median added latency, matching 96% of a two-tier guard-LLM cascade's F1 at 1/385 of its latency with 0% evasion under 13 adversarial transformations; diverting the malicious share cuts production-model token consumption under concurrent flooding with real GCG-suffix payloads by 97.8%; the trained replica agrees with the production model on 92.9% of benign holdout requests, while naive unconditional bait injection collapses to 7.6% and selective camouflaged injection recovers to 88.9%, mapping the recoverable fidelity-traceability frontier; and a loop-trained correction head cuts misrouting of legitimate security research 9x while raising detection F1 to .933.

Han Jin

Independent Researcher

LLM Serving Adversarial Attacks on LLMs LLM Security LLM Routing

Sep 2, 2026cs.LG

The Implications of Linguistic Illegibility for LLM Security

LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term ``linguistic illegibility'' to broadly refer to scenarios in which an LLM's externalized or mechanistically-probed language artifacts fail to represent how the model actually thinks. We argue that the specter of linguistic illegibility is unavoidable for LLMs whose internal computations are not directly expressed via language, but rather math over activation spaces (with lossy translations between activation spaces and natural language happening at the bookends). If linguistic illegibility is always possible, then security mechanisms that rely on a model's linguistic self-reporting (e.g., chain-of-thought monitoring, constitutional self-critique, activation probing for linguistically-defined feature vectors) can never be completely sound; the model sandbox will always need isolation techniques whose guarantees do not depend on reading a model's linguistic state at all. We argue that observing a model's outputs using taint tracking is a promising approach for an effective sandbox: regardless of how a model linguistically self-reports, a taint tracking policy can define, a priori, various pieces of system state that should never be influenced by model-produced data. We also discuss several additional sandboxing mechanisms (e.g., robust virtualization, third-party auditing of sandboxing configurations) which collectively provide a critical floor beneath linguistic monitoring, and would have mitigated recent sandbox exploits by frontier models.

James Mickens

Harvard University

Aug 31, 2026cs.CR

Capability-Gated Language Models: Security Composes, Utility Does Not

Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigured, tiers are multiplied, and artefacts are reissued; inside one set of weights every request meets the same model configuration. This motivates us to define capability-gated deployment: per-principal access control inside one set of weights, whose configurations form a lattice - meets accumulate a principal's restrictions and joins pool a coalition's reach. We instantiate it by sparse rank gating over an existing nested-factorisation mechanism, guide profile search with one-pass attribution, and read every result once from a pre-registered held-out split. Security approximately composes: provably exactly at meets under a monotone-elicitation assumption we falsify pointwise. In two lineages the median held-out meet deepens suppression; the one effect surviving correction strengthens it. Utility does not: individually harmless profiles can compose to retention and fluency damage, and no compositional bound exists.

Patrikas Vanagas, Augustas Mačijauskas, Laurynas Lopata

BPTI Vilnius, Lithuania · Independent Researcher Vilnius, Lithuania · askEarth AG Zürich, Switzerland

Language Model Safety Evaluation LLM Security

Aug 31, 2026cs.CL

Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text

Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such mechanisms can be exploited to inject targeted social biases into aligned models through semantically benign synthetic data. We construct a pipeline in which a misaligned teacher model generates filtered synthetic datasets across domains such as creative writing and code generation, which are then used to fine-tune aligned student models. Our experiments show that benign-looking synthetic data can act as a covert channel for transmitting targeted biases while largely preserving the student model's general task capabilities. These results reveal a previously underexplored security risk in synthetic data-driven LLM training pipelines and highlight the need for improved safeguards. As one possible step toward this goal, we suggest that log-linearity-based scoring may provide a useful signal for screening seemingly benign synthetic data.

Minkyung Cho, Jihyo Kim, SeungWoo Song +4

KAIST · KAIST InnoCORE PRISM-AI Center · Department of Artificial Intelligence, Dankook University

Social Bias in Language Models LLM Security Data Poisoning Attacks

Aug 30, 2026cs.AI

Interpreting and Steering for Safe and Correct Code Generation

Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguish safe from vulnerable generation in them. In this work, we systematically perform a mechanistic interpretation of LLMs, aiming at both understanding how code safety-vs-vulnerability is represented or driven by components in an LM and turning the insights into actionable steering strategies to encourage safer code generation. To this end, we introduce CodeSec-Pairs, a dataset of 9,342 Python safe-and-vulnerable contrastive code pairs, sampled from Llama-3.1-8B-Instruct. Utilizing the dataset, we explore approaches to localize layers and attention heads that relate to code safety, and further experiment with different steering strategies for inference-time vulnerability reduction. In particular, we propose DuoSteer, a double-steering approach that simultaneously applies safety and code-correctness steering to attention heads. In experiments over five vulnerability types, DuoSteer leads to an average of -26.9% vulnerability rate reduction and +7.5% functional correctness improvement, which outperforms not only other steering variants but also prompting and supervised fine-tuning baselines. The advantage also replicates on Qwen-2.5-Coder-7B-Instruct with another 2,500 contrastive pairs sampled from that model.

Hao Yan, Ziyu Yao

Department of Computer Science George Mason University, Fairfax, VA

Mechanistic Interpretability LLM Security Secure Code Generation Activation Steering LLM Code Generation

Aug 30, 2026cs.CL

Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?

The output of a Language Model can be tampered with \emph{while} the model is writing it. A simple test can thus be constructed by evaluating the model's perception of this external perturbation. In this spirit, a simple benchmark is built in which a single word is consistently substituted with another in the generation process. We call this method \emph{Sleight of Word}. Two distinct axes are measured: metrics that relate to the model's surprise, as well as an evaluation of the textual reaction for 19 different open-weight language models.

Alberto Cetoli

Cleo

Language Model Generation Evaluation Language Model Self-Assessment LLM Security Language Model Probing

Aug 28, 2026cs.CR

Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code

Large language models increasingly author Infrastructure-as-Code (IaC), where one insecure default is provisioned straight into production. Prior evaluations report vulnerability counts for models only, and so cannot say whether models are worse than the engineers they assist. We present GenIaC-SecBench: 100 deployment scenarios across 12 model configurations from six vendors, open and closed weights, yielding 1,196 artifacts scanned by three policy engines (Checkov, Trivy, KICS) at complete coverage. Crucially we scan 634 human-authored IaC templates with the identical toolchain, giving the first size-matched human security baseline for this task. Vulnerability density is strongly inverse to artifact size (Spearman

ρ=-0.55

,

p<10^{-77}

), so unmatched comparisons measure size, not security. Size-matched, every configuration exceeds the human baseline at

3.21\times

to

3.87\times

, and the gap widens as tasks get simpler (

4.9\times

at one resource,

1.4\times

at twenty or more). A majority of scenarios prescribe a security state rather than specifying function alone, so we stratify by prompt class: pooled the gap is

3.50\times

, and excluding every scenario that explicitly requests an insecure configuration still leaves all configurations above baseline (

2.4\times

to

4.2\times

). The corpus cannot isolate unprompted default posture, and we say so. Decomposing "reasoning" into standard generation, prompted chain-of-thought, and vendor extended-thinking APIs, extended thinking beats prompted CoT (

-12.0\%

,

p=0.0013

) while prompted CoT alone is indistinguishable from standard (

-1.3\%

, n.s.); it consumes under

1\%

of the output budget, bounding the effect. Two negative results: more deployable models are not more vulnerable (

r=0.158

,

p=0.625

), and complete-case Friedman is uncomputable here, motivating Skillings-Mack. All code and data are released.

Animesh Shaw

LLM Security LLM Code Generation

Aug 11, 2026cs.CR

Backdoor Decontamination Dynamics in LLM Agents

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a known backdoor (defensive poisoning) then to unlearn it, hoping that the original unknown backdoor is removed as a side effect. However, this procedure has uncertain outcomes: the original backdoor may persist or be erased or rerouted, among other possibilities. We introduce a framework for studying these dynamics in tool-calling agents, decoupling trigger, response, teacher, and fine-tuning method across systematic experiments on AgentDyn. Across 115 experiments, defensive poisoning alone erases around 56% of original backdoors; subsequent decontamination then drives almost all survivors to erasure, confirming that trigger recognition and malicious execution are behaviorally dissociable. Interestingly, our experiments find that malicious backdoors never persist when using different triggers of the same general type as the defensive backdoor when followed by decontamination via unlearning. Co-installing up to four backdoors increases resistance (around 36% erased), yet decontaminating a single known co-resident backdoor collaterally clears 52/60 co-residents (87%). Upon visualizing postdecontamination model internals using J-lens, we confirm that although the decontamination restores benign LLM responses, traces of original trigger awareness persist at intermediate layers.

Gabriel Huang, Abhay Puri, Léo Boisvert +4

ServiceNow Research · Mila – Quebec AI Institute · Polytechnique Montréal +3

LLM Backdoor Attacks Backdoor Defense in LLMs LLM Agent Security LLM Security Backdoor Defense LLM Unlearning

Aug 11, 2026cs.CR

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbations) dominate, accounting for 66% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7%, misaligned with real-world risk. Code execution security accounts for 3.5%, and tool-augmented agents 12%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers.

Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari

Florida International University, Miami, Florida, USA · Middle Tennessee State University, Murfreesboro, Tennessee, USA · New Jersey Institute of Technology, Newark, NJ, USA

LLM Agent Security LLM Security Prompt Injection Attacks on AI Agents Tool Access Control for LLM Agents

Aug 10, 2026cs.CR

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

Alexander Panfilov, David Schmotz, Ilia Shumailov +5

MATS Research · ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems +4

Model Extraction Attacks Adversarial Attacks Adversarial Attacks on LLMs Privacy Leakage in Language Models LLM Security Prompt Injection Attacks on LLMs

Aug 10, 2026cs.LG

Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent methods align LRMs using direct refusals or safety rationales, yet often focus on prompt patterns rather than intrinsic attack mechanisms. As a result, these pattern-centric alignments struggle to generalize across diverse jailbreaks, compromising adversarial robustness and reasoning utility. We propose AdvSafe, a dual-adversarial framework that enables LRMs to internalize unsafety knowledge by explicitly deconstructing adversarial mechanisms. This moves beyond pattern-dependent traces, fostering robust cognitive defense without compromising reasoning utility. Our pipeline operates via a two-phase adversarial game. First, in adversarial synthesis, an autonomous agent dynamically crafts deceptive jailbreak prompts, adapting its strategies to breach a strong teacher model. Second, in adversarial extraction, the breached teacher executes a cognitive counter-attack. For every successful jailbreak, the teacher unmasks the camouflage, explaining why the attack succeeds and how such prompts can be identified and mitigated. This dual-adversarial process yields a compact reasoning dataset capturing rich, generalizable unsafety knowledge. Student models trained on this dataset implicitly acquire safety alignment through intrinsic threat comprehension. Experiments show that with only 1K synthesized samples, AdvSafe-aligned LRMs achieve significantly stronger jailbreak robustness than existing baselines, with almost no utility degradation. Furthermore, AdvSafe improves robustness against out-of-distribution prompts, demonstrating that learning unsafety knowledge enables a superior robustness-utility trade-off and generalizes beyond seen attack patterns.

Hongli Shen, Shaopeng Fu, Qinbo Zhang +2

1King Abdullah University of Science and Technology · 2Stony Brook University

Adversarial Training Adversarial Attacks on LLMs LLM Safety Alignment LLM Security Adversarial Robustness of Language Models

Aug 10, 2026cs.CR

Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests. In multi-tenant deployments this cache is shared across tenants, creating a timing side channel: an adversarial tenant can reconstruct another tenant's private prompt by probing cache-hit latency. Three published attacks exploit it -- PROMPTPEEK, EarlyBird and InputSnatch -- reaching up to 100% attack success rate against unprotected vLLM and SGLang, with rates varying by cache architecture and prompt structure. We present KVGov, a governance layer addressing all three attack families' prefix-cache paths under one mechanism. A per-principal salt sigma_p = HMAC_K(secret, principal_id) seeds the block-hash chain, making cache keys cryptographically disjoint across principals. An ablation (N=1000 trials, seed 2026, deterministic judges) isolates this salt as the necessary and sufficient component. KVGov adds ORIGAMI, a Stackelberg water-filling audit scheduler that reduces adversary expected utility by 12.6% at realistic tenant heterogeneity (Gini 0.63), and an evolutionary stability analysis giving a 31.6% adversary-prevalence tipping point below which global caching remains stable. On real hardware (Qwen2.5-7B-Instruct, vLLM 0.26.0, NVIDIA A100) we measure a gate-verified cold/cached TTFT ratio of 0.22, confirming the channel is exploitable at production scale; the defense itself is evaluated in simulation calibrated to those measurements. We replicate the channel on an independent stack (llama.cpp on Apple Metal, ratio 0.093). Finally, isolation and cache efficiency need not conflict: identifying information resides only where prompts diverge, so injecting the salt at that boundary rather than the chain root retains an estimated 93% of the prefix-cache benefit with no cross-principal signal.

Tejasvi C. Addagada

KV Caching KV-Cache Management Privacy Leakage in Language Models LLM Security KV-Cache Reuse

Aug 7, 2026cs.CR

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis. This paper formalizes the structure of prompt-injection artifacts, enabling defenders, red teamers, and cyber threat intelligence (CTI) teams to label, compare, and mutate attacks without relying on fragile string matching. Because large language models compile varied natural-language realizations into identical executable actions, labeling must track attacker intent (tool targets, sinks, and effects) rather than surface wording. We propose a seven-component model (carrier, delivery vector, concealment, context-break, privilege escalation, payload, and return channel) consisting of five artifact fields and two environment fields. This framework unifies roles partially addressed by HOUYI's payload decomposition, the Promptware Kill Chain, and campaign taxonomies, while framing minimal jailbreak frameworks like ReNeLLM as projections onto a restricted subspace. We provide clear labeling rules, a logical analysis record mapping directly to industry CTI schemas, worked examples including EchoLeak (CVE-2025-32711) and an in-the-wild malware AI-evasion sample, and an illustrative agentic flowchart.

Jeremy McHugh

Preamble, Inc.

LLM Security Prompt Injection Attacks Prompt Injection Attacks on LLMs

Aug 7, 2026cs.SE

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools

Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to production, manual harm identification and mitigation are becoming difficult to scale. Although many tools support model evaluation, adversarial testing, runtime guardrails, and observability, the tooling landscape remains fragmented. Tools are typically designed for specific engineering tasks and described in technical terms that do not align with governance frameworks or risk taxonomies, making it difficult to determine which tools address which risks and where critical gaps remain. This paper proposes a structured protocol to automate AI risk mitigation through a taxonomy-driven analysis of open-source LLM evaluation and security tools. We map the capabilities of 21 prominent open-source tools to the 32 subcategories of the extended MIT AI Risk Mitigation and Response Taxonomy. An LLM-assisted retrieval-augmented generation pipeline analyzes source code and documentation to extract capabilities for each taxonomy category. Reliability assessment yielded moderate agreement (Fleiss' Kappa = 0.509) among three independent reviewers. The analysis reveals a highly skewed landscape in which tools cluster around technical and operational controls, while governance, legal and regulatory, and financial and market controls remain largely unaddressed. This motivates a layered risk-mitigation architecture combining tool-based controls with organizational and regulatory processes. The mapping protocol achieved an F1 score of 75.5% after majority voting. Overall, the study provides a practical mapping between enterprise AI risk categories and open-source mitigation capabilities, identifies where human oversight remains necessary, and presents a taxonomy-driven framework applicable to open-source and proprietary solutions.

Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj +4

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

AI Risk Management LLM Security LLM Safety Evaluation

Aug 7, 2026cs.CR

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes backdoor signals and reduces detection performance. Existing adapter-aware methods do not address how to safely use a potentially backdoored adapter. Instead, they either train a defensive adapter to repair a backdoored base model, addressing the inverse problem rather than securing the adapter itself, or rely on a classifier that flags the entire adapter as suspicious and requires separate mitigation. These methods overlook the distinct latent-space signatures produced by trigger-bearing inputs in backdoored adapters. We introduce LoRAScan, the first adapter-aware defense that detects and rejects trigger-bearing inputs at inference time without modifying adapter parameters. Our key observation is that a small subset of LoRA insertion sites, approximately 5%, remains stable across clean inputs but exhibits highly concentrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance insertion sites before model deployment and monitors them during inference. Across standard LLM backdoor benchmarks, LoRAScan rejects approximately 98.49 of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings.

Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1

Michigan Technological University · Miami University · Lehigh University

LLM Backdoor Attacks Backdoor Detection Backdoor Defense in LLMs Low-Rank Adaptation LLM Security

Aug 7, 2026cs.CR

Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models

Most language-model access controls regulate behavior while leaving the same computation available to every request. We study a different systems question: can trusted authorization determine which newly trained parameters are reachable by the forward pass? Policy-Masked Private Experts freezes a pretrained sparse Mixture-of-Experts (MoE) model, trains a disjoint expert branch, and selects the public or private pool before top-k routing. The resulting claim is narrow but testable: under the declared trusted computing base (TCB), an unauthorized request executes no private expert. It does not imply that the public model lacks the same semantic capability. We test this separation between execution control and task utility in Qwen3-30B-A3B and DeepSeek-V2-Lite. Three Qwen BF16 seeds update all 32 private experts while the public fingerprint remains unchanged. Across 64 adversarial scenarios and 96 deny/fail-closed events, unauthorized private execution is zero; independent hooks exactly match 11,616 routed private rows and allow-deny-allow recovery is exact. On two prospectively frozen Qwen benchmarks, the private branch improves exact tool use by 5.0 percentage points (pp) (five versus zero discordances; one-sided Holm p = 0.03125, corresponding two-sided exact p = 0.0625) and 21.3 pp (percentile-bootstrap 95% CI [13.3, 29.3], Holm p = 0.000031). Three arm-blinded model evaluators retain a positive external effect of 18.7 pp (95% CI [9.3, 28.0]). A parameter-matched Lora has similar external utility, but a post-hoc request gate leaves 1,225 adapter calls under deny; the disjoint expert branch leaves none. DeepSeek reproduces the route invariant and gains 27.0 pp. A valid sealed evaluation is near-neutral. These results support auditable, reversible control over a trained parameter path, while showing that useful transfer remains distribution dependent.

Zhuoheng Huang, Mukesh Singh

Independent Researcher

LLM Auditing Sparse Mixture-of-Experts LLM Security Mixture-of-Experts Models

Aug 5, 2026cs.CR

Hardware Design and Security in the Era of Chiplets and LLMs

The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While these paradigms offer unprecedented benefits in yield, modularity, design productivity, etc., they radically expand the hardware attack surface. This paper provides a unified analysis of these frontiers, ranging from attacks on chiplet systems (including hardware stacks for LLM acceleration) across architectural, logical, and physical levels, to various exploits against LLM-driven EDA pipelines. To secure chiplet systems, we review a powerful defense approach that leverages 2.5D split manufacturing and active interposers for physically isolated Root of Trust (RoT) architectures. To secure LLM-driven EDA pipelines, we first identify native threats and then review state-of-the-art defense techniques. Finally, we discuss how LLM systems can advance hardware security efforts for modern systems, including chiplets.

Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz +1

NYU Abu Dhabi · Texas A&M University · NYU Tandon School of Engineering

Electronic Design Automation Cybersecurity LLM Security

Aug 5, 2026cs.CR

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning

Released aligned large language models remain vulnerable to malicious downstream finetuning. Existing defenses are largely designed for the fine-tuning-as-a-service (FTaaS) paradigm or rely on downstream users to follow additional safety procedures, and therefore do not directly address the setting we study: a provider controlled partially protected open-weight (PPOW) release setting in which most weights remain trainable while a small safety-critical component is preserved at release. We propose a Unidirectional Safety Gate (USG), instantiated as a Null Space Cubic Layer together with an Inverse Adapter inserted after the final Transformer layer. During downstream fine-tuning, the cubic layer suppresses or blocks gradients from harmful samples whose hidden states fall in a calibrated protected region, while the Inverse Adapter restores the base model's forward behavior. In practice, we calibrate a threshold using defender-held harmful data, allowing protection to generalize to nearby in-distribution harmful samples. Across six evaluated model-dataset settings, USG keeps post-finetuning attack success rate close to the pre-release level under a fixed release threshold, while maintaining high safe-pass rates on easier settings and exhibiting a clearer safety-utility trade-off on unsafe samples from BeaverTails. These results suggest that release-time representation-space blocking can raise the cost of malicious downstream adaptation without requiring downstream cooperation. The code is available at https://github.com/OpenCausaLab/Gradient-Immunity.

Yuxuan Huang, Xingyu Zeng, Tianhang Zheng +1

Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Shenzhen University of Advanced Technology +1

LLM Safety Alignment LLM Security LLM Safety

Aug 4, 2026cs.CR

An Inline Control Architecture for Language Models in Intelligent Transportation Systems

Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator assistance, and decision support at roadside units and edge nodes. Although these components are not part of safety-critical control loops, they introduce prompt-level attack surfaces that are not addressed by traditional V2X security mechanisms focused on authentication and message integrity. This paper presents Guarded-V2X, an inline semantic guardrail architecture for securing LLM-enabled V2X services under real-time constraints. The proposed system integrates rule-based ingress filtering, a lightweight safety classifier, policy-constrained structured generation, trusted-only retrieval, and post-decision adjudication to enforce machine-checkable safety boundaries prior to downstream execution. Guarded-V2X is evaluated using a four-stage experimental pipeline encompassing intrusion vulnerability analysis, calibration and latency benchmarking, guardrail validation, and robustness under adversarial stress. Experiments are conducted on a V2X-aligned simulated dataset derived from RSU advisories, operator messages, and annotated V2X message summaries. Results show that unguarded and prompt-only baselines retain residual vulnerability under multi-turn adversarial trials, while Guarded-V2X consistently reduces intrusion acceptance success rates and eliminates observed unsafe completions in two-turn settings, without exceeding latency budgets for V2X semantic advisory paths.

Narendra Kumar Dewangan, Mounira Msahli

LTCI, Département Informatique et Réseaux, Télécom Paris, Institut Polytechnique de Paris, France

LLM Guardrails Adversarial Attacks on LLMs LLM Security V2X Communication

Aug 4, 2026cs.CR

A Security-Oriented Lifecycle Model for Large Language Model Systems

Large language models are being integrated into critical infrastructure and enterprise workflows at unprecedented scale,yet the lifecycle frameworks governing their development and operations were designed for operational efficiency rather than security analysis. As a result, security-relevant activities such as data provenance verification, artifact signing, agentic permission control, and decommissioning are often left implicit or assumed to receive due care. Governance frameworks, in turn, organise requirements around risk levels or management processes without clearly linking them to the lifecycle stages where they apply. This paper addresses both deficiencies. We propose a lifecycle model for LLM systems that supports security analysis by structuring it around security-relevant boundaries rather than workflow optimisation. The model comprises 32 stages across four core pipeline layers (Data, Model, Distribution, Application), supported by a 12-stage LLMOps pillar and a 9-category governance pillar. Thirteen stages are introduced here as separate units because they expose distinct security concerns that existing frameworks do not clearly distinguish. A governance mapping synthesising the NIST AI RMF, the EU AI Act, and ISO/IEC 42001 reveals a structural property of the current regulatory landscape: governance evidence concentrates at deployment-facing stages, where systems are visible to regulators, while the most consequential decisions, data selection, alignment strategy, and capability boundaries, are made at development-facing stages, where regulatory visibility is lowest.

Eleftherios Batzolis, George Drosatos, Vassilis Katsouros +1

Department of Informatics, Democritus University of Thrace, Kavala, Greece · Institute for Language and Speech Processing, Athena Research Center, Xanthi, Greece

AI Assurance LLM Security AI Governance

Aug 4, 2026cs.CR

AI Security Leaderboard: Methodology, Results and Minimal Standard

The AI Security Leaderboard is an independent benchmark that ranks the safeguards of frontier AI models from least to most secure. It tests models against the FAR

.

AI Minimal Standard for Safeguards, which represents a minimum bar for security: meeting it does not guarantee a secure model, but failing to meet it guarantees a lack of state-of-the-art security. Version 1.0 covers severe misuse requests across chemical, biological, radiological, nuclear, and explosive (CBRNE) threats and offensive cybersecurity. In this report, we tested four leading models for universal jailbreaks in the context of this minimal standard, and found more than a hundredfold difference in security. Claude Fable 5 and GPT-5.6 Sol held against every attack we ran, with no universal jailbreak found; we estimate they would likely cost more than $14,200 to jailbreak, if it is possible with this methodology at all. Meanwhile, we found hundreds of universal jailbreaks for Grok 4.5 and Gemini 3.1 Pro; each broke for under $300, with universal jailbreaks in Grok's weakest domain, cybersecurity, accessible for as little as $24. The gap is fixable: every weakness we found belongs to a known class of attack that already has a defense deployed in production models. The leaderboard will be updated on a rolling basis as new models are released, and the evaluation methodology and Minimal Standard will be periodically revised to take into account the latest capabilities and the state-of-the-art in safeguards. The leaderboard is available at leaderboard.far.ai.

Jasper Timm, Lukas Struppek, Ziwei Xu +12

LLM Safety Benchmarks Cybersecurity LLM Security LLM Jailbreak Attacks

Aug 4, 2026cs.CR

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

Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this property to optimize LLM serving systems by omitting weight accesses and computations pertaining to inactive neurons. Unfortunately, however, such optimizations create input-dependent weight accesses, which can be leaked over side channels. We present SparSEEty, a new token extraction attack that exploits input-dependent neuron weight accesses introduced by sparsity-exploiting LLM serving systems. SparSEEty first constructs a neuron-activation oracle using neuron weight access side channels during LLM inference, and then inverts the activation traces to reconstruct the input tokens, forming an end-to-end token extraction attack. We instantiate SparSEEty against an LLM serving system protected inside an Intel TDX confidential virtual machine (CVM), addressing three key challenges: (i) constructing a neuron-activation oracle using a combination of side channels exposed by CVMs, (ii) reducing inference-time overheads of neuron activation monitoring for covertness, and (iii) accurately inverting partial binary activation traces back to tokens. Our evaluation shows that SparSEEty can reconstruct both prompt and response tokens with consistently high BLEU scores (>0.95) across various models and datasets, while incurring monitoring overheads of 3.7% to 7.2%.

Yongwan Jo, Jinyoung Park, Euihyun Lee +1

Department of Computer Science Yonsei University

Privacy Leakage in Language Models LLM Security

Aug 3, 2026cs.AI

LaCache: Robust Semantic Caching for LLM Serving

Semantic caching, which reuses responses to semantically similar requests via their embeddings, has seen growing adoption in LLM serving, offering faster responses and reduced costs. Yet existing schemes are fundamentally vulnerable to cache-collision attacks, wherein an adversary pollutes the cache by injecting crafted queries, corrupting responses to subsequent legitimate requests. We present LaCache, a novel semantic caching scheme that addresses this vulnerability through a conceptually simple yet principled redesign. The key insight is that while the adversary has full control over the adversarial query, it has far less control over its response, which must simultaneously satisfy multiple semantic constraints. Rather than checking only the cache hit of a query, LaCache additionally checks the cache hit of its first k (speculatively) decoded tokens. This design yields two concrete benefits. First, it provides formally guaranteed resilience against cache-collision attacks: we prove that it is impossible to craft adversarial queries that simultaneously elicit malicious responses and collide with benign queries. Second, the enriched index supplies additional semantic context for cache retrieval, improving response relevance. Empirical evaluation across diverse LLMs and benchmarks validates both LaCache's security guarantees and efficiency gains, pointing to a promising direction for robust semantic caching.

Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1

Stony Brook University

LLM Serving LLM Security Semantic Caching

Aug 2, 2026cs.CR

DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large language model (LLM) toward an attacker-chosen wrong answer. Prior single-document attacks typically avoid explicitly naming and refuting the correct answer inside the poisoned passage. In this paper, we examine a complementary design and propose \emph{DenialRAG}, a single-document poisoning attack that explicitly names the correct answer, denies it, and presents an attacker-controlled explanation for favoring the wrong answer. By placing both the correct answer and the corresponding poisoned answer inside the same retrieved passage, DenialRAG embeds the conflict directly into the context seen by the generator. We evaluate DenialRAG against four published single-document poisoning attacks across three open-domain question-answering datasets, eight target LLMs from four vendors, and five inference-time defenses. The results show that attack effectiveness is strongly model-dependent: DenialRAG achieves the highest attack success rate (ASR) on all three Mistral-7B datasets and remains effective on several other target LLMs, while other attacks dominate in some model regimes. Defense results show meaningful ASR reductions but non-uniform protection, with each defense leaving residual ASR in some settings. Component-level and cross-model analyses further identify the embedded denial as the most influential tested component and show that different poisoning mechanisms lose effectiveness at different rates across model groups. Together, these results show that RAG poisoning risk cannot be fully characterized by a single attack family or a single target model.

Abay Zhurekbay, Tao Liu, Fan Li

Lawrence Technological University

Knowledge Conflicts in Language Models RAG Poisoning Attacks LLM Security

Jul 30, 2026cs.LG

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint, demonstrates that a malicious parameter server can corrupt a PEFT adapter into a privacy backdoor: by assigning a dedicated memorization neuron to each training sample and ensuring each neuron updates at most once, the server can analytically reconstruct 59%--79% of client training data with high semantic fidelity. Existing defenses---including local differential privacy (LDP) and gradient clipping---either fail against this attack or impose unacceptable utility degradation. We present \textbf{TriShield}, a three-layer deterministic defense that completely prevents NeuroImprint-style reconstruction with zero model utility loss and no additional communication rounds. TriShield consists of: (1) a Parameter Artifact Detector that identifies memory-neuron signatures in distributed model parameters before local training begins; (2) a Stateful Virtual Iteration} mechanism that forces Adam/AdamW's momentum state to irreversibly entangle gradients across virtual steps, invalidating NeuroImprint's closed-form inversion; and (3) a Zero-Utility Orthogonal Projection operator that projects all local gradient updates onto the main-task semantic subspace computed via SVD, physically eliminating any gradient components that carry private memorization. We prove theoretically that after Layers 2 and 3, the mutual information between the uploaded gradient and any individual training sample is zero. Experiments on GPT-2 (117M) and Llama-Guard-3-1B verify that TriShield reduces NeuroImprint reconstruction rate to 0% across all tested attack variants, while maintaining or improving training accuracy, with less than 5% additional GPU computation overhead.

Cheng Wei

Honor Device Co., Ltd., Shenzhen, China

Backdoor Attacks Backdoor Attacks in Federated Learning Backdoor Defense in LLMs Privacy Leakage in Language Models LLM Security Federated Fine-Tuning

Jul 28, 2026cs.CR

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

Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads. Recent work suggests that large language models (LLMs) can automate cluster security remediation, generating configuration patches from Kubernetes Security Posture Management (KSPM) findings without human authoring. Such systems, however, prompt the model with each finding in isolation from the live service call graph, assuming general hardening knowledge suffices. This assumption breaks down whenever a patch must preserve a runtime service dependency invisible to the model: an otherwise compliant fix then carries a destructive functional blast radius, crashing downstream callers or silently severing call edges across the cluster. Whether live cluster context improves patch correctness has not been measured under controlled conditions across multiple dependency classes. We introduce KuTIE (Kubernetes Topology Intelligence Engine), which builds a live cluster context from Istio call edges, Trivy KSPM findings, and the service-account bindings a workload reads, and conditions LLM patch generation on it. It is evaluated on VulnCare, a purpose-built 36-deployment, four-namespace healthcare cluster with 31 injectable findings across seven dependency classes, each labelled by topology dependence against cluster ground truth. Across 248 trials, topology context raises topology-dependent patch correctness from 11.1% to 78.0% (

Δ= 0.669

), a gap that holds for every model and for six of seven classes, from credential and network-policy (

Δ= 0.95

) to role-based access control (

Δ= 0.31

); a topology-independent control exhibits no such effect (

Δ= 0.0

), isolating the result from generic prompt enrichment. Supplying the live service-call graph and the service-account bindings it exposes thus improves remediation of topology-dependent findings well beyond scanner-only context.

Farooq Shaikh

Dynatrace Research, Linz, Austria

Automated Program Repair LLM Prompting Software Security LLM Security

Jul 28, 2026cs.CL

Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models

Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse. Injected fingerprints, i.e., trigger--target pairs embedded in model behavior, offer a practical, black-box-verifiable ownership signal, but existing methods decouple the two stages of the fingerprint life cycle: how a fingerprint is constructed and how it is injected. Existing fingerprinting frameworks suffer from two limitations. Natural-language fingerprints are prone to accidental activation, and garbled fingerprints are easily filtered by perplexity-based detection. Furthermore, decoupling construction from injection leaves the latter unaware of the trigger's linguistic structure, missing the opportunity for targeted optimization. We argue that fingerprint construction should drive injection, and present a unified fingerprinting framework that jointly optimizes both stages. First, LCF constructs code-mixing fingerprints by combining low-resource languages under a semantic-density substitution rule and grammar-biased mixing, yielding triggers whose perplexity sits far below garbled baselines while avoiding the accidental-activation failures of natural-language triggers. Second, LCFEdit injects each fingerprint with a null-space projection derived from high-resource multilingual representations that preserves knowledge, augmented by a cross-lingual alignment step that steers the weight update toward the fingerprint language's representation subspace. This construction-aware injection ensures that the update is linguistically informed and therefore more stable. Extensive evaluations on imperceptibility, detectability, and harmlessness demonstrate persistent ownership verification with negligible impact on utility.

Yongyi Cui, Yue Li, Tianbao Jiang +1

East China Normal University

Language Model Fingerprinting LLM Security

Jul 28, 2026cs.CR

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

Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines such threats as decision-level hijacking. Existing attacks fail to achieve targeted cognitive manipulation without triggering prohibited content or degrading model functionality. To fill this gap, this paper reveals that Bit-Flip Attacks (BFAs) can serve as an attack vector for inducing decision-level hijacking, requiring no real-time interaction or control over the training process, and only a minimal number of weight bits need to be flipped after deployment to achieve stealthy, low-cost, and persistent cognitive manipulation. Therefore, we propose CogBias, a cognitive bias injection framework for LLMs. CogBias converts subjective preferences into optimization signals via a differentiable sentiment evaluator, uses a multi-objective loss to jointly constrain multiple dimensions, and constructs BitScout to locate critical bits, achieving targeted cognitive intervention under an ultra-sparse flip budget. Experiments on Llama-3.2-3B, Mistral-7B, and Qwen2.5-14B, as well as on the commercial recommendation and controversial factual topic scenarios, demonstrate that flipping only a small number of bits stably induces significant stance shifts on target topics, while the impact on non-target tasks and overall output distribution is limited. This work demonstrates that minute perturbations to low-level weight data suffice to undermine the high-level value alignment of LLMs.

Yu Yan, Jiahao Chen, Siqi Lu +6

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

LLM Alignment Adversarial Attacks on LLMs LLM Security