FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems

Artificial Intelligence AI-based Intrusion Detection Systems IDS deployed in energy infrastructure are vulnerable to model theft attacks, which allow adversaries to create evasive traffic offline. Current defences against model extraction rely either on identity-bound query monitoring, which is...

WARD: Adversarially Robust Defense of Web Agents against Prompt Injections

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard models still suffer from limited generalization to unseen...

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP Via OOD Trigger Inversion

Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service MLaaS providers, who adapt vision-language models VLMs such as CLIP to downstream tasks via prompt tuning rather than training from scratch. This semi-honest setting...

SafePickle: Robust and Generic ML Detection of Malicious Pickle-Based ML Models

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution RCE risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires comple...

Sparse Autoencoders Are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering CC-Delta, an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without...

MAD-OOD: A Deep Learning Cluster-Driven Framework for an Out-Of-Distribution Malware Detection and Classification

Out of distribution OOD detection remains a critical challenge in malware classification due to the substantial intra family variability introduced by polymorphic and metamorphic malware variants. Most existing deep learning based malware detectors rely on closed world assumptions and fail to...

False Sense of Security: Why Probing-Based Malicious Input Detection Fails to Generalize

Large Language Models LLMs can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in LLMs' internal representations, and researchers ha...

Coward: toward Practical Proactive Federated Backdoor Defense Via Collision-Based Watermark

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning FL, where malicious clients upload poisoned updates that compromise the global model and undermine the reliability of FL deployments. Existing backdoor detection techniques fall into two...

Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection

Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution OOD detection: A Variational...

TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification Utilizing OOD Data

Federated learning FL systems allow decentralized data-owning clients to jointly train a global model through uploading their locally trained updates to a centralized server. The property of decentralization enables adversaries to craft carefully designed backdoor updates to make the global model...