6 papers
Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution
Minjae Lee, Kyunghyun Cho, Sangdon Park
Aligning large language models (LLMs) with human values is important for safe, efficient, and beneficial AI deployment. However, human values are multifaceted: helpfulness, harmles…
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…
Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards
Minji Jung, Minjae Lee, Yejin Kim +2
LLM leaderboards are widely used to compare models and guide deployment decisions. However, leaderboard rankings are shaped by evaluation priorities set by benchmark designers, rat…
PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair
Wonyoung Kim, Seunggi Min, Minjae Gwon +11
Continuous fuzzing platforms such as OSS-Fuzz uncover large numbers of vulnerabilities, yet the subsequent repair process remains largely manual. Unfortunately, existing Automated…
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…
Online Conformal Abstention 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…