Related papers: Clutch Control: An Attention-based Combinatorial B…

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static…

Fuzzing has gained in popularity for software vulnerability detection by virtue of the tremendous effort to develop a diverse set of fuzzers. Thanks to various fuzzing techniques, most of the fuzzers have been able to demonstrate great…

Fuzzing is highly effective in detecting bugs due to the key contribution of randomness. However, randomness significantly reduces the efficiency of fuzzing, causing it to cost days or weeks to expose bugs. Even though directed fuzzing…

Curvature information -- particularly, the largest eigenvalue of the loss Hessian, known as the sharpness -- often forms the basis for learning rate tuners. However, recent work has shown that the curvature information undergoes complex…

Coverage guided fuzzing (CGF) is an effective testing technique which has detected hundreds of thousands of bugs from various software applications. It focuses on maximizing code coverage to reveal more bugs during fuzzing. However, a…

Optimization is commonly employed to determine the content of web pages, such as to maximize conversions on landing pages or click-through rates on search engine result pages. Often the layout of these pages can be decoupled into several…

JavaScript (JS) engine vulnerabilities pose significant security threats affecting billions of web browsers. While fuzzing is a prevalent technique for finding such vulnerabilities, there have been few studies that leverage the recent…

Prompting has emerged as the dominant paradigm for adapting large, pre-trained transformer-based models to downstream tasks. The Prompting Decision Transformer (PDT) enables large-scale, multi-task offline Reinforcement Learning (RL)…

We consider a new setting of online clustering of contextual cascading bandits, an online learning problem where the underlying cluster structure over users is unknown and needs to be learned from a random prefix feedback. More precisely, a…

Many software projects employ manual code review to gatekeep defects and vulnerabilities in the code before integration. However, reviewers often work under time pressure and rely primarily on static inspection, leaving the dynamic aspects…

Online advertising and product recommendation are important domains of applications for multi-armed bandit methods. In these fields, the reward that is immediately available is most often only a proxy for the actual outcome of interest,…

Most existing approaches in Context-Aware Recommender Systems (CRS) focus on recommending relevant items to users taking into account contextual information, such as time, location, or social aspects. However, few of them have considered…

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions,…

We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation operation, provides…

Fuzzing is one of the most effective technique to identify potential software vulnerabilities. Most of the fuzzers aim to improve the code coverage, and there is lack of directedness (e.g., fuzz the specified path in a software). In this…

Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and…

Fuzzing is a popular dynamic program analysis technique used to find vulnerabilities in complex software. Fuzzing involves presenting a target program with crafted malicious input designed to cause crashes, buffer overflows, memory errors,…

Smart contracts are Turing-complete programs that are executed across a blockchain. Unlike traditional programs, once deployed, they cannot be modified. As smart contracts carry more value, they become more of an exciting target for…

The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose…

We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach…