31 papers
Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection
Rahul Deivasigamani, Sayeda Faatin Alvi, Derqui Andrea +2
The rise of autonomous AI agents represents a major paradigm shift in how users interact with mobile devices. Frameworks such as MobileRun and Mobile-Use can autonomously navigate…
Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
Roberto Riaño, Gorka Abad, Stjepan Picek +1
The paper introduces a clean‑label backdoor attack for spiking neural networks that subtly reshapes the timing of events in target‑class training streams, achieving near‑perfect at…
SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation
Xiaoyun Xu, Lichao Wu, Jona te Lintelo +2
Large language models routinely generate code with exploitable security flaws. Prior literature attributes this limitation to a lack of security expertise, steering current defense…
GoodVibe: Security-by-Vibe for LLM-Based Code Generation
Maximilian Thang, Lichao Wu, Sasha Behrouzi +4
Large language models (LLMs) are increasingly used for code generation in fast, informal development workflows, often referred to as vibe coding, where speed and convenience are pr…
You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera +2
The open-source ecosystem has accelerated the democratization of Large Language Models (LLMs) through the public distribution of specialized Low-Rank Adaptation (LoRA) modules. How…
MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
Jona te Lintelo, Lichao Wu, Marina KrÄek +2
Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However, this sparse activation paradig…