12 papers
Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation
Sanket Badhe, Priyanka Tiwari
The paper introduces SkillSec-Eval, a framework for assessing security risks throughout the entire lifecycle of reusable LLM agent skills, from repository admission to evolution.
Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability
Alicia Parrish, Rajat Shinde, Sanket Badhe +57
Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…
Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI
Jonghyun Chung, Sanket Badhe
As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calendar entries, files, screenshots,…
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning
Sanket Badhe, Deep Shah
Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternati…
Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey
Jonghyun Chung, Rishabh Chaddha, Sanket Badhe +3
The proliferation of adversarial synthetic content, accelerated by Generative AI (GenAI) is rendering traditional reactive detection methods ineffective. This survey synthesizes em…
The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods
Sanket Badhe, Priyanka Tiwari, Deep Shah
Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a phenomenon we define as Renor…