RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning

ground-truth answers, and no access to model internals; it compares the model's own answers under counterfactual contexts. On poisoned Natural Questions at 5--30\% poison ratios, adversarial retriever

Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks

Model Context Protocol (MCP) enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates

HAMLOCK: HArdware-Model LOgically Combined attacK

networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify inputs with a specific trigger, are often detectable because

A vulnerability in keras-team/keras versions <= 3.15.0 allows for

TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

factors: attack performance, stealthiness, time complexity, and required poison rates. For example, achieving high attack performance typically demands a high poison rate and prolonged training, which undermines stealthiness, making

Hidden State Poisoning Attacks against Mamba-based Language Models

their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA). Our benchmark RoBench25 allows evaluating a model's information retrieval capabilities when subject to HiSPAs, and confirms

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the global model. Although detection methods can identify and remove malicious

Steering Vectors are an Adversarial Attack Surface

verify. We test the attack on two open-weight model families and eight model-attribute combinations, observing that poisoned vectors reach an absolute attack success rate

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

data poisoning and backdoor attacks show that VIA significantly increases the presence of poisoning content in synthetic data and correspondingly raises the attack success rate (ASR) on downstream models

Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models

environments. This work proposes a novel framework that uses large language models (LLMs) to perform poisoning detection and sanitization in HAR systems, utilizing zero-shot, one-shot, and few-shot

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

model in which a subtle word (e.g., ``cool'') induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning

Hidden State Poisoning Attacks against Mamba-based Language Models

their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA). Our benchmark RoBench-25 allows evaluating a model's information retrieval capabilities when subject to HiSPAs, and confirms

DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization

demonstrate that DPOison-VL achieves up to 98\% ASR with only 2\% poisoned data and exhibits cross-model transferability, while largely preserving clean accuracy and general utility. Our findings reveal

MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study

models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned

Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks

loses only 0.9\% F1-macro at 10\% poisoning and delays target-class collapse from 60\% to 70\% poisoning compared with raw models. These results demonstrate that neuromorphic temporal encoding

SoK: Unlearnability and Unlearning for Model Dememorization

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds imperceptible

Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation

post-defense intervals included 0 in all eight settings, while the cross-model pro-poisoning results retained small positive residual point estimates of +0.045 to +0.063. For 20 candidate documents

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models

conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets

Confundo: Learning to Generate Robust Poison for Practical RAG Systems

present Confundo, a learning-to-poison framework that fine-tunes a large language model as a poison generator to achieve high effectiveness, robustness, and stealthiness. Confundo provides a unified framework