Related papers: Ranking Warnings of Static Analysis Tools Using Re…

Deep Neural Networks (DNNs) are used in a wide variety of applications. However, as in any software application, DNN-based apps are afflicted with bugs. Previous work observed that DNN bug fix patterns are different from traditional bug fix…

A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding: unobserved variables may influence both the actions taken by the agent and the observed outcomes. Hidden confounding can compromise the…

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal…

Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX…

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

This paper investigates runtime monitoring of perception systems. Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars. In these applications, failure of perception…

Static malware analysis is well-suited to endpoint anti-virus systems as it can be conducted quickly by examining the features of an executable piece of code and matching it to previously observed malicious code. However, static code…

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning. Many works achieve disentanglement upon information bottlenecks (IB). Despite their elegant mathematical…

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge…

Review websites, such as TripAdvisor and Yelp, allow users to post online reviews for various businesses, products and services, and have been recently shown to have a significant influence on consumer shopping behaviour. An online review…

Fault localization has been determined as a major resource factor in the software development life cycle. Academic fault localization techniques are mostly unknown and unused in professional environments. Although manual debugging…

Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics. To reduce the residual risk for unexpected DNN behaviour and provide evidence for their trustworthy…

While static analysis is useful in detecting early-stage hardware security bugs, its efficacy is limited because it requires information to form checks and is often unable to explain the security impact of a detected vulnerability. Large…

Context: Automated software defect prediction (SDP) methods are increasingly applied, often with the use of machine learning (ML) techniques. Yet, the existing ML-based approaches require manually extracted features, which are cumbersome,…

Web applications are permanently being exposed to attacks that exploit their vulnerabilities. In this work we investigate the application of machine learning techniques to leverage Web Application Firewall (WAF), a technology that is used…

This report examines the synergy between Large Language Models (LLMs) and Static Application Security Testing (SAST) to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high…

Consumers increasingly rate, review and research products online. Consequently, websites containing consumer reviews are becoming targets of opinion spam. While recent work has focused primarily on manually identifiable instances of opinion…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

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…