AI Threat Alert
(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
iSpy module easily evades standard malware scanners, while the associated poisoned inputs and resulting compromised models bypass typical inspection tools. We demonstrate the practicality of this threat with an implementation
Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
significantly improving stealthiness and practicality. Furthermore, we introduce visual adversarial perturbations on poisoned samples to modulate the model's learning of textual triggers, enabling a controllable and adjustable TGB attack
A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG
including missing evidence, poisoning, incorrect answers, and hallucinations. In a high-stakes MedQA-USMLE case study, we further show that poisoned retrieved evidence can mislead models across scales, leading
MemoryGraft: 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
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
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
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
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
documents are preferentially retrieved at inference time, enabling targeted manipulation of model outputs. We study gradient-guided corpus poisoning attacks against modern RAG pipelines and evaluate retrieval-layer defenses that
Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a fundamental trade-off between transferability and stealthiness. Static trigger-based