Concept-Guided Backdoor Attack on Vision Language Models

first, Concept-Thresholding Poisoning (CTP), uses explicit concepts in natural images as triggers: only samples containing the target concept are poisoned, causing the model to behave normally in all other

Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice

backdoor attacks are particularly concerning because VFL not only enables malicious contributors to poison the model during training, but also allows them to activate the backdoor at inference time

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

porting optimizers from one domain (e.g., LLM jailbreak) to new domains (e.g., corpus-poisoning embedding model). In all, TROPT significantly lowers the barrier to adopting and advancing discrete text optimization

Serverless AI Security: Attack Surface Analysis and Runtime Protection Mechanisms for FaaS-Based Machine Learning

characterize the attack surface across five categories: function-level vulnerabilities (cold start exploitation, dependency poisoning), model-specific threats (API-based extraction, adversarial inputs), infrastructure attacks (cross-function contamination, privilege escalation

Web Technologies Security in the AI Era: A Survey of CDN-Enhanced Defenses

mitigate while reducing data movement and enhancing compliance, yet introduces new risks around model abuse, poisoning, and governance

GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning

cited, and adopted by models. Existing fact-verification benchmarks and evaluation frameworks do not provide the controlled evidence environments needed to assess robustness against GEO poisoning. We therefore propose

Threat Modeling and Attack Surface Analysis of IoT-Enabled Controlled Environment Agriculture Systems

federated transfer learning, adversarial agronomic schedules that exploit crop biology rather than computational models, and reward poisoning of reinforcement-learning energy optimizers. Physical impact analysis quantifies crop loss timelines from

Why Backdooring Neural Networks is so Easy?

budget -- the poison fraction $π$ and trigger strength $α$ needed to construct successful yet stealthy attacks. Motivated by recent empirical evidence that poisoning large language models can require a nearly

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning

MirageBD generally achieves over 90% attack success rate across four datasets and five models with a poison ratio of only 5%. Moreover, even under rigorous evaluations such as trigger perturbations

IAMRAGBENCH: Benchmarking Authorization Expansions in LLM-Generated AWS IAM Policies under RAG Poisoning

Large language models (LLMs) using retrieval-augmented generation (RAG) can synthesize Amazon Web Services (AWS) Identity and Access Management (IAM) policies from tasks and operational documents. Attacker-controlled context

Correlated Failures of AI Approval Monitors

counting approvals, whatever inputs the monitors share. Monitors that share a base model or a poisoned input, however, may fail together. We borrow the fail-prone systems of distributed computing

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved documents. Existing detection methods typically rely on auxiliary classifiers or additional

TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes

rate from 0.75 to 0.90 at equal token cost. A poisoned runbook telling the model to delete the namespace was rejected by the guard every run; with the guard disabled

Secure Retrieval-Augmented Generation against Poisoning Attacks

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but also

Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference

insecure LLM pipelines, making them vulnerable to multiple attacks such as data poisoning, prompt injection, and model theft. Although several security techniques (input/output sanitization, decentralized learning, access control management

CKAN MCP Server: Cache-key canonicalization collision enables cache confusion

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work: the attacker plants a dormant payload into an agent's long-term

(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