AI Threat AlertMemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic
TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement
detectors, so apparently clean data can still redirect the trained model. We therefore ask which properties a poison set must preserve for the attack to remain effective. A small poison
Online AutoML: Evaluating Poisoning Attacks on Adversarial Training Defense Strategy in IoT Networks
model's learning process. The objective is to diminish model efficacy, instill biases, induce misclassifications, or include concealed backdoors that may be attacked during implementation. In streaming contexts, poisoning attacks
FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
data; on the other hand, they may compromise clients to launch poisoning attacks that corrupt the global model. To balance accuracy and security, we propose FedFG, a robust FL framework
FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who compromise model integrity through Byzantine attacks, data poisoning, or adaptive adversarial behaviors
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
third-party or internet data is common. Recent studies show CL models are vulnerable to data-poisoning backdoor attacks, but their generalization and robustness are underexplored. We systematically evaluate existing
From Theory to Practice: Evaluating Data Poisoning Attacks and Defenses in In-Context Learning on Social Media Health Discourse
This study explored how in-context learning (ICL) in large language models can be disrupted by data poisoning attacks in the setting of public health sentiment analysis. Using tweets
Cisco Integrated AI Security and Safety Framework Report
threats now span content safety failures (e.g., harmful or deceptive outputs), model and data integrity compromise (e.g., poisoning, supply-chain tampering), runtime manipulations (e.g., prompt injection, tool and agent misuse
Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
detectability, and defense reliability. Next, we synthesize attack-defense interactions across poisoning, backdoors, Byzantine manipulation, privacy leakage, model extraction, network/orchestration attacks, Sybil behavior, and strategic participation. We further compare layered
Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
inspection are blind by construction, while feature-space methods detect the poison only in selected settings. Our model-free detector, based on per-step event mass, detects the evaluated temporal
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
Backdoor attacks create significant security threats to language models by
Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic threat models and are thus less useful in practice
State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
Vision-Language-Action (VLA) models are widely deployed in safety
Osmosis Distillation: Model Hijacking with the Fewest Samples
generated by dataset distillation methods, where an adversary can perform a model hijacking attack with only a few poisoned samples in the synthetic dataset. To reveal this threat, we propose
Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence
evidence, but it also opens a data-layer attack surface: poisoned corpus entries can steer outputs without changing model parameters. Existing defenses and traceback methods are largely passage-level, which
LoRA-Patch: Defending Against Backdoored LoRA Adapters via Directional Steering
typically sanitize backdoored models by updating, pruning, distilling, or mixing model parameters. However, these approaches are misaligned with adapter-based deployment, where the trusted base model is expected to remain
Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks
adversarial attacks, including direct prompt injection, indirect prompt injection, memory poisoning, and backdoor attacks, which exploit the model's openness to prompt injection and tool manipulation. In this work
MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks
email, document, crypto) with six server variants (baseline and hardened) and model three attack families: tool-metadata poisoning, puppet servers, and multimodal image-to-tool chains, in a unified, trace
Test-Time Attention Purification for Backdoored Large Vision Language Models
defenses across diverse datasets and backdoor attack types, while preserving the model's utility on both clean and poisoned samples
Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
semantic deviation caused by label flipping, both of which make poisoned graphs easily detectable by anomaly detection models. To address this, we propose DPSBA, a clean-label backdoor framework that