Related papers: Speculative Dereferencing of Registers:Reviving Fo…
Practical attacks that exploit speculative execution can leak confidential information via microarchitectural side channels. The recently-demonstrated Spectre attacks leverage speculative loads which circumvent access checks to read…
We present a novel mechanism to construct a covert channel based on page faults. A page fault is an event that occurs when a process or a thread tries to access a page of memory that is not currently mapped to its address space. The kernel…
Recent work presented at USENIX Security 2025 (SEC'25) claims that occupancy-based attacks can recover AES keys from the MIRAGE randomized cache. In this paper, we examine these claims and find that they arise from a modeling flaw in the…
Windows OS kernel memory is one of the main targets of cyber-attacks. By launching such attacks, hackers are succeeding in process privilege escalation and tampering with users data by accessing kernel mode memory. This paper considers a…
Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single…
Randomizing the address-to-set mapping and partitioning of the cache has been shown to be an effective mechanism in designing secured caches. Several designs have been proposed on a variety of rationales: (1) randomized design, (2)…
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…
This retrospective paper describes the RowHammer problem in Dynamic Random Access Memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 conference~\cite{rowhammer-isca2014}. RowHammer is a prime (and perhaps the…
The Rete forward inference algorithm forms the basis for many rule engines deployed today, but it exhibits the following problems: (1) the caching of all intermediate join results, (2) the processing of all rules regardless of the necessity…
As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user images. The widely adopted technology uses local feature descriptors, which are…
Modern microprocessors depend on speculative execution, creating vulnerabilities that enable transient execution attacks. Prior defenses target speculative data leakage but overlook false dependencies from partial address aliasing, where…
Backdoor and data poisoning attacks can achieve high attack success while evading existing spectral and optimisation based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input…
Caches on the modern commodity CPUs have become one of the major sources of side-channel leakages and been abused as a new attack vector. To thwart the cache-based side-channel attacks, two types of countermeasures have been proposed:…
This paper explores inference-time data leakage risks of deep neural networks (NNs), where a curious and honest model service provider is interested in retrieving users' private data inputs solely based on the model inference results.…
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning…
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side…
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…
In the recent past, we have witnessed the shift towards attacks on the microarchitectural CPU level. In particular, cache side-channels play a predominant role as they allow an attacker to exfiltrate secret information by exploiting the CPU…
The security of billions of devices worldwide depends on the security and robustness of the mainline Linux kernel. However, the increasing number of kernel-specific vulnerabilities, especially memory safety vulnerabilities, shows that the…