AI Threat AlertReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models
Vision--Language Models (VLMs) are increasingly deployed in safety-critical applications, yet remain vulnerable to backdoor attacks. Existing methods primarily manipulate final outputs, often producing reasoning traces that are inconsistent
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
fine-tuning set can degrade the model's alignment. Two recent alignment-stage defenses address this problem at different levels of the model. Vaccine improves the robustness of hidden embeddings
Bypassing Prompt Injection Detectors through Evasive Injections
Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to task drift; deviations from a user's intended instruction due to injected
Autonomous Cyber Defense in Connected Vehicles: A Multi-Agent Approach to V2X Security
resolving safety-security conflicts using complementary sensor observations. The cloud tier refines detection models through Byzantine fault-tolerant federated learning and redistributes updated weights to the fleet. Every timing constraint
Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation
Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security implications remain dangerously underexplored. This paper conducts the first systematic exploration
How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation
Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also exposes a critical security vulnerability: adversarial documents injected into
Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems
intelligent models are vulnerable to adversarial machine learning attacks, particularly backdoor attacks. In a backdoor attack, an adversary injects malicious patterns into the training data so that the model behaves
Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic
Backdoor Attacks Against Speech Language Models
resulting model inherit vulnerabilities from all of its components. In this work, we present the first systematic study of audio backdoor attacks against speech language models. We demonstrate its effectiveness
Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
safety filters, and highly configurable, allowing for surgical targeting of specific environments or model providers. To evaluate the real-world impact, we conduct extensive experiments across three representative claw-style
Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling retrieval mechanisms with generative models, RAG systems improve factual grounding and adaptability across domains. However
Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme
server (PS) cannot access individual local updates, making it difficult to identify and exclude poisoned gradients. The challenge is further exacerbated under non-independent and identically distributed (Non-IID) training
MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
systematically study multimodal memory poisoning, an overlooked yet practical attack surface in web-agent systems. We propose MemVenom, a unified black-box attack framework that poisons graph-structured external memory
Beyond Wireless Security: Covert Communications in Large Language Model-enabled Edge Networks
Large language model (LLM)-enabled edge networks (LLMENs) offer mobile users high-quality and low-latency AI-generated content services in the 6G era. However, unlike typical edge networks, LLMENs
Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning
this paper, we revisit the backdoor threat to standard FL (a single global model) under a more realistic setting where triggers must be semantically meaningful, in-distribution, and visually plausible
PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architecture with provable integrity guarantees
Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining normal behavior on clean samples. Since these artificial triggers are absent
Backdoor Decontamination Dynamics in LLM Agents
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