Skip to content

Author

G. Suh

We have 5 of 195 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Nov 2026

MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark

This paper presents MetaPI, an extensible toolkit that automatically identifies plausible injection points, generates realistic attack objectives, optimizes adaptive payloads, and validates attacks in the real environment, and enables scalable and consistent security evaluation across diverse and evolving agent ecosyst...

Pei-Ran Wang, Chong Xiang, Wen-Jie Qu et al. · 0 citations
Preprint Aug 2026

PIPES: Securing Agent Perception with Provenance and Priors

Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We show that this gap enables state-corruption attacks, in which attacker-controlled content makes environmental claims beyond the informational a...

Sanjay Kariyappa, Severin Klingler, G. Suh · 0 citations
#machine learning Preprint Oct 2026

Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience

Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, lim...

Zi-Xu Wang, Hao Li, Feng Gao et al. · 1 citation
Preprint Aug 2026

Trusted Hardware Acceleration for Function Secret Sharing

The distributed function accelerator (DFA), a hardware accelerator that targets the dominant primitive in FSS: distributed point function (DPF) generation and evaluation, combines a high-throughput fixed-function engine for AES-based pseudorandom number generation with a lightweight programmable unit for protocol-speci...

Pengzhi Huang, Kiwan Maeng, G. Suh · 0 citations
Review Sep 2026

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain, guided by model behavior, domain specifications, and fresh-context adversarial review to reject benchmark-specific rules.

Nanxi Li, Ying-Zi Ma, Yu-Long Cao et al. · 4 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.