Related papers: DAPPER: A Performance-Attack-Resilient Tracker for…
NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untargeted bit-flips in victim data like weights of machine…
DRAM-based memory is a critical factor that creates a bottleneck on the system performance since the processor speed largely outperforms the DRAM latency. In this thesis, we develop a low-cost mechanism, called ChargeCache, which enables…
In recent years, Rowhammer has attracted significant attention from academia and industry alike. This technique, first published in 2014, flips bits in memory by repeatedly accessing neighbouring memory locations. Since its discovery,…
Rowhammer poses a significant security challenge for modern computers, specifically affecting Dynamic Random Access Memory(DRAM). Given society's growing reliance on computer systems, ensuring the reliability of hardware is of utmost…
We experimentally demonstrate the effects of read disturbance (RowHammer and RowPress) and uncover the inner workings of undocumented read disturbance defense mechanisms in High Bandwidth Memory (HBM). Detailed characterization of six real…
The state-of-the-art predictive maintenance (PdM) techniques have shown great success in reducing maintenance costs and downtime of complicated machines while increasing overall productivity through extensive utilization of…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Many adversarial attacks belong to the category of dense attacks, which…
Deep regression models are used in a wide variety of safety-critical applications, but are vulnerable to backdoor attacks. Although many defenses have been proposed for classification models, they are ineffective as they do not consider the…
Tor, a widely utilized privacy network, enables anonymous communication but is vulnerable to flow correlation attacks that deanonymize users by correlating traffic patterns from Tor's ingress and egress segments. Various defenses have been…
Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…
Diffusion models exhibit notable fragility when faced with adversarial prompts, and strengthening attack capabilities is crucial for uncovering such vulnerabilities and building more robust generative systems. Existing works often rely on…
Systems-on-chip (SoCs) are becoming heterogeneous: they combine general-purpose processor cores with application-specific hardware components, also known as accelerators, to improve performance and energy efficiency. The advantages of…
Microarchitectural vulnerabilities increasingly undermine the assumption that hardware can be treated as a reliable root of trust. Prevention mechanisms often lag behind evolving attack techniques, leaving deployed systems unable to assume…
Anomaly detection is a crucial step for preventing malicious activities in the network and keeping resources available all the time for legitimate users. It is noticed from various studies that classical anomaly detectors work well with…
Adversarial attacks on Neural Network weights, such as the progressive bit-flip attack (PBFA), can cause a catastrophic degradation in accuracy by flipping a very small number of bits. Furthermore, PBFA can be conducted at run time on the…
Recent studies reveal that local differential privacy (LDP) protocols are vulnerable to data poisoning attacks where an attacker can manipulate the final estimate on the server by leveraging the characteristics of LDP and sending carefully…
Cache side channel attacks are increasingly alarming in modern processors due to the recent emergence of Spectre and Meltdown attacks. A typical attack performs intentional cache access and manipulates cache states to leak secrets by…
Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity due to its capacity to reduce computational demands through…
With web applications becoming a preferred method of presenting graphical user interfaces to users, software vulnerabilities affecting web applications are becoming more and more prevalent and devastating. Some of these vulnerabilities,…
Graph partitioning has long been seen as a viable approach to address Graph DBMS scalability. A partitioning, however, may introduce extra query processing latency unless it is sensitive to a specific query workload, and optimised to…