SEW

SEW: Watermarking con codificación de estilo para código generado por LLM Enlace al artículo 📖 📰 Noticias 📢 ¡NUEVO! El artículo de SEW está disponible en arXiv: arXiv:2609.39414. 30 de septiembre de 2026 📢 El código oficial de SEW ha sido publicado en GitHub. 30 de septiembre de 2026 🔍 Motivación...

Patcher: Post-Hoc Patching of Backdoored Large Language Models

Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical wh...

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...

PROVEX: Enhancing SOC Analyst Trust with Explainable Provenance-Based IDS

Modern intrusion detection systems IDS leverage graph neural networks GNNs to detect malicious activity in system provenance data, but their decisions often remain a black box to analysts. This paper presents a comprehensive XAI framework designed to bridge the trust gap in Security Operations...

Explainable Ensemble Learning for Graph-Based Malware Detection

Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks GNNs have shown promise in this domain by modeling rich structural dependencies in graph-based program representations such a...

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs

Recent studies have shown that Large Language Models LLMs are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a phrase and focus on the attack's effectiveness, offering limite...

Mitigating Watermark Stealing Attacks in Generative Models Via Multi-Key Watermarking

Watermarking offers a promising solution for GenAI providers to establish the provenance of their generated content. A watermark is a hidden signal embedded in the generated content, whose presence can later be verified using a secret watermarking key. A threat to GenAI providers are \emphwaterma...

Autoregressive Images Watermarking through Lexical Biasing: an Approach Resistant to Regeneration Attack

Autoregressive AR image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking techniques are primarily designed for diffusion models, where...

Interpretable Anomaly Detection in Encrypted Traffic Using SHAP with Machine Learning Models

The widespread adoption of encrypted communication protocols such as HTTPS and TLS has enhanced data privacy but also rendered traditional anomaly detection techniques less effective, as they often rely on inspecting unencrypted payloads. This study aims to develop an interpretable machine...

The Chronicles of Foundation AI for Forensics of Multi-Agent Provenance

Provenance is the chronology of things, resonating with the fundamental pursuit to uncover origins, trace connections, and situate entities within the flow of space and time. As artificial intelligence advances towards autonomous agents capable of interactive collaboration on complex tasks, the...