AI Threat Alert
Steering Vectors are an Adversarial Attack Surface
verify. We test the attack on two open-weight model families and eight model-attribute combinations, observing that poisoned vectors reach an absolute attack success rate
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
data poisoning and backdoor attacks show that VIA significantly increases the presence of poisoning content in synthetic data and correspondingly raises the attack success rate (ASR) on downstream models
Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models
environments. This work proposes a novel framework that uses large language models (LLMs) to perform poisoning detection and sanitization in HAR systems, utilizing zero-shot, one-shot, and few-shot
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
model in which a subtle word (e.g., ``cool'') induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning
Hidden State Poisoning Attacks against Mamba-based Language Models
their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA). Our benchmark RoBench-25 allows evaluating a model's information retrieval capabilities when subject to HiSPAs, and confirms
SoK: Unlearnability and Unlearning for Model Dememorization
Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds imperceptible
The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets
Confundo: Learning to Generate Robust Poison for Practical RAG Systems
present Confundo, a learning-to-poison framework that fine-tunes a large language model as a poison generator to achieve high effectiveness, robustness, and stealthiness. Confundo provides a unified framework
CSC: Turning the Adversary's Poison against Itself
compromise model utility through unlearning methods that lead to accuracy degradation. This paper conducts a comprehensive analysis of backdoor attack dynamics during model training, revealing that poisoned samples form isolated
Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment
preserving the intended poisoning effect. Empirical results demonstrate that this cost-minimization post-processing can significantly reduce poisoning costs over baselines, particularly when the reward model's feature dimension
Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
induced behaviors and restore normal functionality. Building on this, we purify the poisoned dataset using the compromised model itself, then fine-tune the model on the purified data to recover
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely on clustering, which requires sufficient data
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
backdoor attacks, where adversaries poison a small subset of data to implant hidden behaviors. Despite this growing risk, defenses for instruction-tuned models remain underexplored. We propose MB-Defense (Merging
Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning
models from three providers (N=30 per model), where models autonomously invoke a graph query tool and reason from results. The result is unambiguous: every tested model trusts poisoned data
Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models
large language models, but it is notably ineffective at removing backdoor behaviors from poisoned pretrained models when fine-tuning on clean dataset. Contrary to the common belief that this weakness
Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems
making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be more vulnerable to introspection
AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
emph{data decryption attacks and watermark removal attacks}; (2) Data$\rightarrow$Model (D$\rightarrow$M): including \emph{poisoning, harmful fine-tuning attacks, and jailbreak attacks}; (3) Model$\rightarrow$Data
TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models
Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation. Such assumptions reduce both the stealthiness
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
poisoning attack targeting the reasoning process of medical LLMs during SFT. Unlike backdoor attacks, our method injects poisoned rationales into few-shot training data, leading to stealthy degradation of model
Gray-Box Poisoning of Continuous Malware Ingestion Pipelines
high volume of novel threats. This work investigates a realistic gray-box poisoning threat model targeting these pipelines. Using the secml_malware framework, we generate problem-space adversarial binaries through