Multi-Targeted Graph Backdoor Attack

based attack. Our analysis on four GNN models confirms the generalization capability of our attack which is effective regardless of the GNN model architectures and training parameters settings. We further

RIFLE: Robust Distillation-based FL for Deep Model Deployment on Resource-Constrained IoT Networks

TinyML models, collaboratively train global models by sharing gradients with a central server while preserving data privacy. However, as data heterogeneity and task complexity increase, TinyML models often become insufficient

Open WebUI: Redis Cache Keys tool_servers and terminal_servers

A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks

crucial to system providers. This technical report targets the threat model most relevant to industry practitioners: although model training is performed in-house, training data is sourced from possibly-compromised

Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems

poisoning) attacks in practical RAG deployments. RAGDefender operates during the post-retrieval phase, leveraging lightweight machine learning techniques to detect and filter out adversarial content without requiring additional model training

Robustness of Anomaly Detection Models for Industrial Control Systems under Training-Time Data Contamination

poisoning methods. Contamination budgets from 1% to 10% are evaluated using clean validation and test sets under a unified offline protocol. The results show that robustness is strongly model-dependent

Stealing Reasoning Traces from Proprietary LLM APIs

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

Safety, Security, and Cognitive Risks in Neuro-Symbolic AI

threat model extending MITRE ATLAS with 11 NeSy-specific tactic extensions and a five-profile attacker taxonomy; (3) a symbolic-layer threat catalogue covering knowledge graph (KG) poisoning, ontology-merging

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI

model inference. Agents accumulate sensitive context, hold credentials, and operate across pipelines no single party fully controls, enabling prompt injection, context exfiltration, credential theft, and inter-agent message poisoning. Current

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

poisoning. Second, we analyzed the data collected from the challenge to examine the prevalence and success rates of different attack types, providing insights into how specific jailbreak strategies exploit model

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers

systematic analysis of poisoning risks in LLM-based prompt optimization. Using HarmBench, we find systems are substantially more vulnerable to manipulated feedback than to query poisoning alone: feedback-based attacks

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools

large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol

Adaptive Intrusion Detection System Leveraging Dynamic Neural Models with Adversarial Learning for 5G/6G Networks

network security by providing robust, real-time threat detection and response capabilities. Unlike conventional models, which require costly retraining to update knowledge, the proposed framework integrates incremental learning algorithms, reducing

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

models, including architectures, training paradigms, and inference mechanisms. We then examine the literature through four lenses: Attacks, Defenses, Evaluation, and Deployment. We survey training-time threats such as data poisoning

Critical Evaluation of Quantum Machine Learning for Adversarial Robustness

three threat models-black-box, gray-box, and white-box. We implement representative attacks in each category, including label-flipping for black-box, QUID encoder-level data poisoning for gray

A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences

Machine learning systems trained on untrusted data are vulnerable to data and backdoor poisoning attacks, in which an adversary corrupts training and test samples to manipulate predictions at inference time

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query time. This makes RAG useful for private data, fast

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a trust-boundary-centric survey of foundation-model

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

model to generate a specific, seemingly innocuous word. Once merged into the dialogue history, this self-generated word becomes the trigger. When a later harmful query arrives, the model detects

Privacy-Preserving Federated Learning from Partial Decryption Verifiable Threshold Multi-Client Functional Encryption

cooperate to train the model without directly exchanging their own private data, but the gradient leakage problem still threatens the privacy security and model integrity. Although the existing scheme uses