This paper presents a system-level framework to mitigate collisions and improve retargeting of sign language generation outputs for humanoid robot execution.

The paper introduces Symbolicate-Enrich-Sample, a pipeline that efficiently filters millions of functions in a Windows OS to create a highly prioritized, manageable shortlist of potential vulnerabilit…

The paper introduces Symbolicate-Enrich-Sample, a low-cost pipeline that drastically reduces the search space of a whole operating system by prioritizing vulnerable functions, turning millions of pote…

The paper introduces a sample-wise targeted adversarial attack that successfully misclassifies only specific, triggered inputs during test-time adaptation while maintaining the overall label distribut…

The paper introduces THREAT, a novel reasoning-driven framework that efficiently discovers highly effective and targeted jailbreak prompts for LLMs, revealing previously unknown safety vulnerabilities…

The paper introduces Semantic-level UI Element Injection, a novel red-teaming technique that overlays misleading UI elements onto screenshots to significantly improve the attack success rate against s…

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

The paper proposes a Distribution-aware Dynamic Guidance (DDG) strategy to mitigate catastrophic overfitting and the robustness-accuracy trade-off inherent in Fast Adversarial Training (FAT) by dynami…

The paper introduces the concept of 'conditional misalignment,' demonstrating that common interventions designed to reduce emergent misalignment can fail by only masking misaligned behavior until the…

ReSkill is an RL-in-the-loop framework that reconciles skill creation and policy optimization by automatically creating, testing, and refining modular skills alongside the agent's policy learning, lea…

MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable…

The paper proposes RESSAP, a novel ensemble framework that significantly enhances the robustness of machine learning classifiers against adversarial evasion attacks by combining feature selection, ens…

PACT is a Pareto-aware active learning controller that significantly reduces the false-positive investigation burden in low-prevalence security alert streams without sacrificing recall.

Automation-Exploit is a multi-agent LLM framework that enables adaptive offensive security by using a digital twin to safely test and execute high-risk memory-corruption exploits on live targets.

The paper proposes ReuseRL, a method that improves agent generalization in Reinforcement Learning by enforcing structural compressibility of successful agent trajectories into reusable skills.

This paper proposes a density-aware attack that constructs triggers by placing poisoned samples in low-density regions of the clean data distribution, achieving high attack success rates even after st…

The paper addresses the failure of fixed-price inference in resource-constrained pricing controllers by developing a target-aware controller that tracks local densities and provides certified, shrinki…