Related papers: Crash-Consistent Checkpointing for AI Training on …
We demonstrate how AI-powered cybersecurity tools can be turned against themselves through prompt injection attacks. Prompt injection is reminiscent of cross-site scripting (XSS): malicious text is hidden within seemingly trusted content,…
Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…
In this study, we explore the impact of relaxing data consistency in parallel machine learning training during a failure using various parameter server configurations. Our failure recovery strategies include traditional checkpointing, chain…
The increasing inclusion of Machine Learning (ML) models in safety critical systems like autonomous cars have led to the development of multiple model-based ML testing techniques. One common denominator of these testing techniques is their…
Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…
Evaluating the correctness of code generated by AI is a challenging open problem. In this paper, we propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. The method uses…
Deep learning-based semiconductor defect inspection has gained traction in recent years, offering a powerful and versatile approach that provides high accuracy, adaptability, and efficiency in detecting and classifying nano-scale defects.…
Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals. Provided the intractably large size of such input spaces, the…
As hardware systems grow in complexity, security verification must keep up with them. Recently, artificial intelligence (AI) and large language models (LLMs) have started to play an important role in automating several stages of the…
Memory safety bugs remain in the top ranks of security vulnerabilities, even after decades of research on their detection and prevention. Various mitigations have been proposed for C/C++, ranging from language dialects to instrumentation.…
Atomicity violation is one of the most serious types of bugs in concurrent programs. Synchronizations are commonly used to enforce atomicity. However, it is very challenging to place synchronizations correctly and sufficiently due to…
Reasoning about safety, security, and other dependability attributes of autonomous systems is a challenge that needs to be addressed before the adoption of such systems in day-to-day life. Formal methods is a class of methods that…
Large language models (LLMs) are increasingly deployed in real-world applications ranging from chatbots to agentic systems, where they are expected to process untrusted data and follow trusted instructions. Failure to distinguish between…
Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…
Generative adversarial networks (GANs) and diffusion models have dramatically advanced deepfake technology, and its threats to digital security, media integrity, and public trust have increased rapidly. This research explored zero-shot…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
Continuous Integration (CI) enforces repository-level correctness through multi-stage workflows and is central to modern software development, yet diagnosing and repairing CI failures remains challenging. Unlike traditional program repair,…
Cyber intrusion attacks that compromise the users' critical and sensitive data are escalating in volume and intensity, especially with the growing connections between our daily life and the Internet. The large volume and high complexity of…
Software vulnerabilities in source code pose serious cybersecurity risks, prompting a shift from traditional detection methods (e.g., static analysis, rule-based matching) to AI-driven approaches. This study presents a systematic review of…
Standard evaluation metrics for machine learning -- accuracy, precision, recall, and AUROC -- assume that all errors are equivalent: a confident incorrect prediction is penalized identically to an uncertain one. For discrete commitment…