Related papers: MOAT: Securely Mitigating Rowhammer with Per-Row A…

A Mobile Ad-Hoc Network is a collection of mobile nodes that are dynamically and arbitrarily located in such a manner that the interconnections between nodes are capable of changing on continual basis. Due to security vulnerabilities of the…

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities…

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

In cloud computing environments, multiple tenants are often co-located on the same multi-processor system. Thus, preventing information leakage between tenants is crucial. While the hypervisor enforces software isolation, shared hardware,…

Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision Trees, Support Vector Machines, Random Forests, Logistic…

In the field of adversarial robustness, there is a common practice that adopts the single-step adversarial training for quickly developing adversarially robust models. However, the single-step adversarial training is most likely to cause…

Graph prompt tuning has emerged as a promising paradigm to effectively transfer general graph knowledge from pre-trained models to various downstream tasks, particularly in few-shot contexts. However, its susceptibility to backdoor attacks,…

This paper proposes a Priority-driven Accelerator Access Management (PAAM) framework for multi-process robotic applications built on top of the Robot Operating System (ROS) 2 middleware platform. The framework addresses the issue of…

Analog crossbar arrays consisting of emerging memory devices can greatly alleviate the computational strain required by vector matrix multiplications for neural network applications. The ability to produce spin orbit torque-magnetic…

The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve scaling efficiency by activating only a small subset of parameters per token, but their…

We propose Remote Attestation with TOCTOU Avoidance (RATA): a provably secure approach to address the RA TOCTOU problem. With RATA, even malware that erases itself before execution of the next RA, can not hide its ephemeral presence. RATA…

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…

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

Intrinsic susceptibility of deep learning to adversarial examples has led to a plethora of attack techniques with a broad common objective of fooling deep models. However, we find slight compositional differences between the algorithms…

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers. Meanwhile, most deep learning models are known to be vulnerable to adversarial examples that are crafted with small…

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…