Related papers: A Simulation-based Evaluation Framework for Inter-…

DRAM scaling has exacerbated the RowHammer vulnerability. To counter this, JEDEC recently introduced Per Row Activation Counting (PRAC) with the Alert Back-Off protocol as an optional DDR5 feature. While promising, PRAC requires per-row…

Recent research efforts focus on reducing the computational and memory overheads of Large Language Models (LLMs) to make them feasible on resource-constrained devices. Despite advancements in compression techniques, non-linear operators…

Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks…

The adoption of high-performance multi-core platforms in avionics and automotive systems introduces significant challenges in ensuring predictable execution, primarily due to shared resource interferences. Many existing approaches study…

Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human…

Empirical Risk Minimization (ERM) based machine learning algorithms have suffered from weak generalization performance on data obtained from out-of-distribution (OOD). To address this problem, Invariant Risk Minimization (IRM) objective was…

Submodular maximization is an optimization problem benefiting many machine learning applications, where we seek a small subset best representing an extremely large dataset. We focus on the federated setting where the data are locally owned…

This paper presents a method for robust optimization for online incremental Simultaneous Localization and Mapping (SLAM). Due to the NP-Hardness of data association in the presence of perceptual aliasing, tractable (approximate) approaches…

Modern embedded systems are evolving toward complex, heterogeneous architectures to accommodate increasingly demanding applications. Driven by SWAP-C constraints, this shift has led to consolidating multiple systems onto single hardware…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Wireless systems must be resilient to jamming attacks. Existing mitigation methods based on multi-antenna processing require knowledge of the jammer's transmit characteristics that may be difficult to acquire, especially for smart jammers…

Rowhammer attacks that corrupt level-1 page tables to gain kernel privilege are the most detrimental to system security and hard to mitigate. However, recently proposed software-only mitigations are not effective against such kernel…

In this paper we provide an implementation, evaluation, and analysis of PowerHammer, a malware (bridgeware [1]) that uses power lines to exfiltrate data from air-gapped computers. In this case, a malicious code running on a compromised…

Memory spatial errors, i.e., buffer overflow vulnerabilities, have been a well-known issue in computer security for a long time and remain one of the root causes of exploitable vulnerabilities. Most of the existing mitigation tools adopt a…

Network address shuffling is one of moving target defense (MTD) techniques that can invalidate the address information attackers have collected based on the current network IP configuration. We propose a software-defined networking-based…

Processing-using-DRAM (PuD) is a promising paradigm for alleviating the data movement bottleneck using DRAM's massive internal parallelism and bandwidth to execute very wide operations. Performing a PuD operation involves activating…

The Internet of Things (IoT) faces tremendous security challenges. Machine learning models can be used to tackle the growing number of cyber-attack variations targeting IoT systems, but the increasing threat posed by adversarial attacks…

The digitalization of substations enlarges the cyber-attack surface, necessitating effective detection and mitigation of cyber attacks in digital substations. While machine learning-based intrusion detection has been widely explored, such…

Neural networks are successful in various applications but are also susceptible to adversarial attacks. To show the safety of network classifiers, many verifiers have been introduced to reason about the local robustness of a given input to…

Bounded Model Checking (BMC) is a widely used software verification technique. Despite its successes, the technique has several limiting factors, from state-space explosion to lack of completeness. Over the years, interval analysis has…