3 accepted papers
Exploration of dynamic environments with sparse rewards is a significant challenge in Reinforcement Learning, often leading to inefficient exploration and brittle policies. To address this, we introduce a novel graph-based intrinsic reward using Effective Resistance, a metric from spectral graph the…
Recent jailbreak attempts on Large Language Models (LLMs) have shifted from algorithm-focused to human-like social engineering attacks, with persuasion-based techniques emerging as a particularly effective subset. These attacks evolve rapidly, demonstrate high creativity, and boast superior attack s…
Contemporary jailbreak attacks on Large Language Models (LLMs) employ sophisticated techniques with obfuscated content to bypass safety guardrails. Existing defenses either use computationally intensive LLM verification or require adversarial fine-tuning, leaving models vulnerable to advanced attack…