Related papers: Adelie: Continuous Address Space Layout Re-randomi…

Practical implementations of quantum key distribution (QKD) have been shown to be subject to various detector side-channel attacks that compromise the promised unconditional security. Most notable is a general class of attacks adopting the…

Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifically, it has been…

In vulnerability assessments, software component-based CVE attribution is a common method to identify possibly vulnerable systems at scale. However, such version-centric approaches yield high false-positive rates for binary distributed…

Linux kernel tuning is essential for optimizing operating system (OS) performance. However, existing methods often face challenges in terms of efficiency, scalability, and generalization. This paper introduces OS-R1, an agentic Linux kernel…

EIP-7702 introduces a delegation-based authorization mechanism that allows an externally owned account (EOA) to authenticate a single authorization tuple, after which all subsequent calls are routed to arbitrary delegate code. We show that…

Current radio frequency (RF) sensors at the Edge lack the computational resources to support practical, in-situ training for intelligent spectrum monitoring, and sensor data classification in general. We propose a solution via Deep Delay…

Memory utilization can be reduced by merging identical memory blocks into copy-on-write mappings. Previous work showed that this so-called memory deduplication can be exploited in local attacks to break ASLR, spy on other programs,and…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Over the last decade, researchers have extensively explored the vulnerabilities of Android malware detectors to adversarial examples through the development of evasion attacks; however, the practicality of these attacks in real-world…

The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software platforms. They also allow for more open…

Evaluating the programming robustness of large language models (LLMs) is paramount for ensuring their reliability in AI-based software development. However, adversarial attacks exhibit fundamental limitations that compromise fair robustness…

We introduce a novel design for in-situ training of machine learning algorithms built into smart sensors, and illustrate distributed training scenarios using radio frequency (RF) spectrum sensors. Current RF sensors at the Edge lack the…

In this paper, we study the problem of localizing the sensors' positions in presence of denial-of-service (DoS) attacks. We consider a general attack model, in which the attacker action is only constrained through the frequency and duration…

IP headers include a 16-bit ID field. Our work examines the generation of this field in Windows (versions 8 and higher), Linux and Android, and shows that the IP ID field enables remote servers to assign a unique ID to each device and thus…

Binary function classifiers play a crucial role in maintaining the security and integrity of software systems by detecting malicious code and unauthorized modifications. However, machine learning-based classifiers are vulnerable to…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary…

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…

Manual RTL design and optimization remains prevalent across the semiconductor industry because commercial logic and high-level synthesis tools are unable to match human designs. Our experience in industrial datapath design demonstrates that…

Randomized smoothing is a leading approach for constructing classifiers that are certifiably robust against adversarial examples. Existing work on randomized smoothing has focused on classifiers with continuous inputs, such as images, where…