From the 1 of 4 linked papers with an AI index.
4 papers
PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair
Wonyoung Kim, Seunggi Min, Minjae Gwon +11
PatchIsland is a system that coordinates multiple LLM agents to automatically generate patches for vulnerabilities discovered by continuous fuzzing pipelines, using a two‑phase ded…
Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
Charvi Rastogi, Mukul Bhutani, Minsuk Kahng +13
Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for t…
Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback
Minjae Lee, Yoonjae Jung, Sangdon Park
As interactive generative systems are increasingly deployed in real-world applications, their tendency to generate unreliable or false responses raises serious concerns. Conformal…
ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
Taesoo Kim, HyungSeok Han, Soyeon Park +43
We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 20…