arXiv subjects

Jingbo Su

Publications and source records attributed to Jingbo Su.

2 recordsLinked to original sources

arXiv2026

ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to provide broad, flexible functionalities or achieve high performance. However, it is inherently difficult to achieve both. We propose ANNLib to address this gap. ANNLib is a library that provides a programming framework to achieve high performance and flexible functionalities for ANNS systems, based on popular graph-based ANNS algorithms. We carefully decouple and independently optimize both the algorithm and the data structure components in an ANNS system. In addition, we integrate state-of-the-art algorithms and data structures as modules in ANNLib, as well as our new designs. Users can choose combinations of components to support sophisticated settings with high performance, such as filtered search, fully dynamic updates, historical queries on snapshots, and range searches. Our experiments show that our new solution provides a simple interface for various applications, and achieves comparable or even better performance to previous work specifically for each application.

cs.LG↗

arXiv2024

Enhancing Adversarial Attacks through Chain of Thought

Large language models (LLMs) have demonstrated impressive performance across various domains but remain susceptible to safety concerns. Prior research indicates that gradient-based adversarial attacks are particularly effective against aligned LLMs and the chain of thought (CoT) prompting can elicit desired answers through step-by-step reasoning. This paper proposes enhancing the robustness of adversarial attacks on aligned LLMs by integrating CoT prompts with the greedy coordinate gradient (GCG) technique. Using CoT triggers instead of affirmative targets stimulates the reasoning abilities of backend LLMs, thereby improving the transferability and universality of adversarial attacks. We conducted an ablation study comparing our CoT-GCG approach with Amazon Web Services auto-cot. Results revealed our approach outperformed both the baseline GCG attack and CoT prompting. Additionally, we used Llama Guard to evaluate potentially harmful interactions, providing a more objective risk assessment of entire conversations compared to matching outputs to rejection phrases. The code of this paper is available at https://github.com/sujingbo0217/CS222W24-LLM-Attack.

cs.CL↗