Related papers: DAPPER: A Performance-Attack-Resilient Tracker for…

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…

The escalating sophistication of cyber-attacks and the widespread utilization of stealth tactics have led to significant security threats globally. Nevertheless, the existing static detection methods exhibit limited coverage, and…

With proliferation of DNN-based applications, the confidentiality of DNN model is an important commercial goal. Spatial accelerators, that parallelize matrix/vector operations, are utilized for enhancing energy efficiency of DNN…

Cyber attacks and malware are now more prevalent than ever and the trend is ever upward. There have been several approaches to attack detection including resident software applications at the root or user level, e.g., virus detection, and…

Control-flow attacks, usually achieved by exploiting a buffer-overflow vulnerability, have been a serious threat to system security for over fifteen years. Researchers have answered the threat with various mitigation techniques, but…

This work addresses a strategy to mitigate jamming attack on low-latency communication by a Full-Duplex (FD) adversary in fast-fading channel conditions. The threat model is such that the FD adversary can jam a frequency band and measure…

Deepfake detection systems deployed in real-world environments are subject to adversaries capable of crafting imperceptible perturbations that degrade model performance. While adversarial training is a widely adopted defense, its…

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

Fault-tolerant routing (FTR) in Networks-on-Chip (NoCs) has become a common practice to sustain the performance of multi-core systems with an increasing number of faults on a chip. On the other hand, usage of third-party intellectual…

Today's datacenter applications are underpinned by datastores that are responsible for providing availability, consistency, and performance. For high availability in the presence of failures, these datastores replicate data across several…

The cache plays a key role in determining the performance of applications, no matter for sequential or concurrent programs on homogeneous and heterogeneous architecture. Fixing cache misses requires to understand the origin and the type of…

Realizing delay-capacity in intermittently connected mobile networks remains a largely open question, with state-of-the-art routing schemes typically focusing either on delay or on capacity. We show the feasibility of routing with both high…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

With the rapid growth of Multi-access Edge Computing (MEC), secure and efficient computation offloading from user equipment (UEs) to edge access points (APs) is critical. However, DISCO intelligent reflective surface-based fully-passive…

Hybrid attention architectures are becoming an increasingly important paradigm for improving LLM inference efficiency while preserving model quality, making hybrid architecture design a central problem. Existing designs often rely on manual…

The popularity of Machine Learning as a Service (MLaaS) has led to increased concerns about Model Stealing Attacks (MSA), which aim to craft a clone model by querying MLaaS. Currently, most research on MSA assumes that MLaaS can provide…

Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical…

Federated learning (FL) enables collaborative model training through model parameter exchanges instead of raw data. To avoid potential inference attacks from exchanged parameters, differential privacy (DP) offers rigorous guarantee against…

Oblivious RAM (ORAM) hides the memory access patterns, enhancing data privacy by preventing attackers from discovering sensitive information based on the sequence of memory accesses. The performance of ORAM is often limited by its inherent…

Dynamic Random Access Memory (DRAM) is the prevalent memory technology used to build main memory systems of almost all computers. A fundamental shortcoming of DRAM is the need to refresh memory cells to keep stored data intact. DRAM refresh…