4 citations · 7 across the 6 of their papers we have counts for
7 papers
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels
Yongwan Jo, Jinyoung Park, Euihyun Lee +1
Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this propert…
SoK: AI-Augmented Binary Reversing
Yujeong Kwon, Yiyue Zhang, Kexin Pei +2
Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to…
SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
Giyeong Oh, Saejin Kim, Woohyun Cho +4
Recently, LoRA and its variants have become the de facto strategy for training and sharing task-specific versions of large pretrained models, thanks to their efficiency and simplic…
dMVX: Secure and Efficient Multi-Variant Execution in a Distributed Setting
Alexios Voulimeneas, Dokyung Song, Per Larsen +2
Multi-variant execution (MVX) systems amplify the effectiveness of software diversity techniques. The key idea is to run multiple diversified program variants in lockstep while pro…
DMON: A Distributed Heterogeneous N-Variant System
Alexios Voulimeneas, Dokyung Song, Fabian Parzefall +4
N-Variant Execution (NVX) systems utilize software diversity techniques for enhancing software security. The general idea is to run multiple different variants of the same program…
SoK: Sanitizing for Security
Dokyung Song, Julian Lettner, Prabhu Rajasekaran +4
The C and C++ programming languages are notoriously insecure yet remain indispensable. Developers therefore resort to a multi-pronged approach to find security issues before advers…
PartiSan: Fast and Flexible Sanitization via Run-time Partitioning
Julian Lettner, Dokyung Song, Taemin Park +3
Sanitizers can detect security vulnerabilities in C/C++ code that elude static analysis. Current practice is to continuously fuzz and sanitize internal pre-release builds. Sanitiza…