activity
20242026
collaborators

11 papers

cs.CR2026

Antares: Foundation Models for Agentic Vulnerability Localization

Supriti Vijay, Aman Priyanshu, Didier Chapoteau +8

Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We prese…

cs.CL2026

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Shayan Talaei, Abhinav Chinta, Devvrit Khatri +3

Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale. Such preferential biases can be intro…

cs.SE2026

FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines

Paul Kassianik, Baturay Saglam, Huaibo Zhao +4

Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We present Fully…

cs.AI2026

Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report

Zhuoran Yang, Ed Li, Jianliang He +18

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived fro…

cs.CL2026

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations

Baturay Saglam, Paul Kassianik, Blaine Nelson +3

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs li…

cs.LG2025

Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents

Jane H. Lee, Baturay Saglam, Spyridon Pougkakiotis +2

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constrai…