DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classification

includes a poisoned model detection strategy that leverages neuron-wise magnitude analysis for attack goal identification and Gaussian Mixture Model (GMM)-based clustering. DEFEND discards poisoned model contributions in each

intended model, as it will open a different model each time. Additionally, an attacker can exploit this vulnerability to perform data model poisoning by creating a model with the same

Stealthy World Model Manipulation via Data Poisoning

three stages of the poisoning pipeline: pre-training detection of poisoned transitions, robust training during fine-tuning, and test-time monitoring of the resulting world model. Across diverse continuous-control

ToxScreen: Detecting Whether an LLM Has Been Poisoned

concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned. To evaluate whether a defender can recover such

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

tasks. In this paper, we present Poison-with-Style (PwS), a practical and stealthy model poisoning attack targeting CLLMs. Unlike prior attacks that assume an active adversary capable of directly

Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missions

solution BALANCE (Fang et al.) that does not provide model consistency, DFL-C achieves better model accuracy against untargeted model poisoning attacks and comparable resilience against backdoor attacks, with

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning

settings, poisoned document-summary pairs exhibit abnormally high training influence, enabling detection via influence-function analysis with semantic consistency checks. In black-box settings, poisoned models display two to three

artifacts belonging to other users. This can lead to unauthorized cross-user writes, model supply chain poisoning, and arbitrary code execution when compromised models are loaded. The issue

Evading Chain-of-Thought Monitoring Through Model Poisoning

assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoors

EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning

Federated learning faces increasing threats from model poisoning attacks, which harms its application to improve privacy. Existing defense methods typically rely on fixed thresholds or perform clustering with a fixed

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

layers of the supply chain: direct poisoning of finetuning data, pre-backdoored base models, and environment poisoning, a novel attack vector that exploits vulnerabilities specific to agentic training pipelines. Evaluated

Sequential Data Poisoning in LLM Post-Training

propose the threat model of sequential data poisoning, where multiple adversaries separately poison the SFT and preference datasets. Under this threat model, we identify the single-attacker illusion: each adversary

Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips

surface. In the context of federated model adaptation, we introduce a novel category of backdoor attack against FL systems that relies on model poisoning based on hardware-fault attacks. More

Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents

without centralizing local datasets. However, the FFT-enabled IoA systems remain vulnerable to model poisoning attacks, where adversaries can upload malicious updates to the server to degrade the performance

The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models

detectable watermark. PLWs pose a novel threat to users of unified multimodal models: A poisoned model can retain utility while covertly turning image generation into a channel for privacy leakage

VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models

large language models (LLMs), which can generate fluent and deceptive content at scale. This work investigates the vulnerability of neural ranking models to corpus poisoning attacks, in which an adversary

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

resulting in a form of ``clean label'' poisoning. Unlike prior targeted poisoning attacks that explicitly require target task samples in the poisoned data, we demonstrate that thought-transfer achieves

MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning

MemCatalyst, a set of data poisoning tools, aiming to amplify the data auditing performance on VLMs. MemCatalyst employs two strategies: Poisoning Text (PT) and Poisoning Image (PI). MemCatalyst forces VLMs

Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks

model training pipelines. This study evaluates the susceptibility of four widely used classifiers, Random Forest, Gradient Boosting Machine, Logistic Regression, and Deep Neural Network models, against multiple poisoning strategies using

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks

these models are significant in developing multi-modal applications. Therefore, this paper proposes SecureLearn, a two-layer attack-agnostic defense to defend multiclass models from poisoning attacks. It comprises