5 papers
Multi-Channel Spread-Spectrum Code Watermarking
Soohyeon Choi, Debin Gao, Yue Duan
Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generati…
MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks
Hyo Seo Kim, Gang Luo, Can Chen +3
Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover opera…
Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMs
Reinelle Jan Bugnot, Soohyeon Choi, Hoon Wei Lim +1
Jailbreaking attacks on large language models pose a significant threat to AI safety by enabling the generation of harmful or restricted content. While prior work has explored both…
Understanding and Characterizing Obfuscated Funds Transfers in Ethereum Smart Contracts
Zhang Sheng, Tan Kia Quang, Shen Wang +3
Scam contracts on Ethereum have rapidly evolved alongside the rise of DeFi and NFT ecosystems, utilizing increasingly complex code obfuscation techniques to avoid early detection.…
PDLogger: Automated Logging Framework for Practical Software Development
Shengcheng Duan, Yihua Xu, Sheng Zhang +2
Logging is indispensable for maintaining the reliability and diagnosability of modern software, yet developers still struggle to decide where and how to log effectively. Existing a…