SRFed: Mitigating Poisoning Attacks in Privacy-Preserving Federated Learning with Heterogeneous Data

develop a privacy-preserving defensive model aggregation mechanism based on DEFE. This mechanism filters poisonous models under Non-IID data by layer-wise projection and clustering-based analysis. Theoretical analysis

RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models

party) fine-tuned models may introduce critical trust issues, as the training data and adaptation process of these models are often opaque. Thus, adversaries (even model providers) may embed hidden

CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models

propose the Clean-Label Backdoor Attack on VLMs via Diffusion Models (CBV), which leverages diffusion models to generate natural poisoned examples via score matching. Specifically, CBV modifies the score during

FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning

necessary attack-free levels in various attack scenarios due to: 1) not tailoring poisoned local model detection to TLFAs, 2) not excluding malicious vehicular clients based on historical behavior

FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning

threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to severe

HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning

backdoor samples in the representation space. Finally, selective parameter poisoning and proximity-aware updates constrain the poisoned model within the vicinity of the global model, enhancing its stability and persistence

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization

data poisoning in the federated adaptation setting. FedPoisonTTP distills a surrogate model from adversarial queries, synthesizes in-distribution poisons using feature-consistency, and optimizes attack objectives to generate high-entropy

Beyond Denial-of-Service: The Puppeteer's Attack for Fine-Grained Control in Ranking-Based Federated Learning

Descending Edges to align the global model with the target model, and (ii) widening the selection boundary gap to stabilize the global model at the target accuracy. Extensive experiments across

Theory of Continual Learning Against Data Poisoning Attacks

latter regime, we derive a robust defense that minimizes the model's sensitivity to poisoned features, provably accelerating the convergence rate. Extensive experiments on realistic tasks further validate our theoretical

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs

Poison-to-Poison (P2P), a general and effective backdoor defense algorithm. P2P injects benign triggers with safe alternative labels into a subset of training samples and fine-tunes the model

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation

datasets frequently lack security verification and are highly susceptible to data poisoning attacks. Such poisoning can cause models to generate syntactically valid but insecure hardware modules that bypass standard functionality

OPFL: Optimistic Verification of Federated Learning via Empirical Boundary

verify whether clients follow the prescribed training procedure or submit malicious updates, such as model poisoning. A natural approach is to replay client training for verification. However, privacy-preserving replay

vulnerability in `nltk.downloader` in nltk/nltk versions <= 3.9.4 allows for cross-package resource and model poisoning. The downloader extracts package archives into shared namespaces such as `corpora/` and `taggers/` instead

Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure

security suffer from two critical vulnerabilities: susceptibility to Byzantine attacks where malicious participants poison model updates, and inadequacy against future quantum computing threats that can compromise cryptographic aggregation protocols. This

On The Dangers of Poisoned LLMs In Security Automation

tuned Llama3.1 8B and Qwen3 4B models, we demonstrate how a targeted poisoning attack can bias the model to consistently dismiss true positive alerts originating from a specific user. Additionally

Python code when loaded, bypassing Picklescan's safety checks and enabling supply-chain poisoning of shared model files

Structure-Aware Distributed Backdoor Attacks in Federated Learning

across different model architectures. This assumption overlooks the impact of model structure on perturbation effectiveness. From a structure-aware perspective, this paper analyzes the coupling relationship between model architectures

CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks

State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performance. However, Hidden State Poisoning Attacks (HiSPAs), a recently

Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning

track how internal preferences between competing facts evolve across checkpoints, layers, and model scales. Even moderate poisoning (50-100%) flips over 55% of responses from correct to counterfactual while leaving

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce