Information Theoretic Adversarial Training of Large Language Models

Large language models LLMs remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to...

GoodVibe: Security-By-Vibe for LLM-Based Code Generation

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 prioritized, and security requirements are rarely made explicit. In this setting, models frequently produce functionally...

Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning Vs. Full Fine-Tuning

This study examines whether Low-Rank Adaptation LoRA fine-tuned Large Language Models LLMs can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware classification. Achieving trustworthy malware detection, particularly when...

ARMOR: Robust Reinforcement Learning-Based Control for UAVs under Physical Attacks

Unmanned Aerial Vehicles UAVs depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physical attacks, such as GPS spoofing, that can corrupt state estimates and lead to unsafe behavior. While reinforcement learning RL offers adaptive control...

Efficient RL-Based Cache Vulnerability Exploration by Penalizing Useless Agent Actions

Cache-timing attacks exploit microarchitectural characteristics to leak sensitive data, posing a severe threat to modern systems. Despite its severity, analyzing the vulnerability of a given cache structure against cache-timing attacks is challenging. To this end, a method based on Reinforcement...

FERRET: Private Deep Learning Faster and Better Than DPSGD

We revisit 1-bit gradient compression through the lens of mutual-information differential privacy MI-DP. Building on signSGD, we propose FERRET--Fast and Effective Restricted Release for Ethical Training--which transmits at most one sign bit per parameter group with Bernoulli masking. Theory: We...