Related papers: CopyCat: Controlled Instruction-Level Attacks on E…

For trusted execution environments (TEEs), remote attestation permits establishing trust in software executed on a remote host. It requires that the measurement of a remote TEE is both complete and fresh: We need to measure all aspects that…

Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling platforms through structured output APIs, but the…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against…

Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, system commands, and external communication channels. While…

Recently, the new ciphertext side channels resulting from the deterministic memory encryption in Trusted Execution Environments (TEEs), enable ciphertexts to manifest identifiable patterns when being sequentially written to the same memory…

Real-time and cyber-physical systems need to interact with and respond to their physical environment in a predictable time. While multicore platforms provide incredible computational power and throughput, they also introduce new sources of…

Internet of Things (IoT) devices sit at the intersection of unwieldy software complexity and unprecedented attacker access. This unique position comes with a daunting security challenge: how can I protect both proprietary code and…

Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client…

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the malware's API call sequences and non-sequential features…

Besides cryptographic secrets, side-channel attacks also leak sensitive user input. The most accurate attacks exploit cache timings or interrupt information to monitor keystroke timings and subsequently infer typed words and sentences.…

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…

Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. However, recent work exposes a critical vulnerability of DC to…

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…

In the recent years, cybersecurity has gained high relevance, converting the detection of attacks or intrusions into a key task. In fact, a small breach in a system, application, or network, can cause huge damage for the companies. However,…

Distributed data analytics platforms (i.e., Apache Spark, Hadoop) provide high-level APIs to programmatically write analytics tasks that are run distributedly in multiple computing nodes. The design of these frameworks was primarily…

Cache timing attacks allow attackers to infer the properties of a secret execution by observing cache hits and misses. But how much information can actually leak through such attacks? For a given program, a cache model, and an input, our…

Many modern IoT applications rely on the Constrained Application Protocol (CoAP) because of its efficiency and seamless integrability in the existing Internet infrastructure. One of the strategies that CoAP leverages to achieve these…

This work tackles a critical challenge in AI safety research under limited compute: given a fixed computation budget, how can one maximize the strength of iterative adversarial attacks? Coarsely reducing the number of attack iterations…

Microarchitectural timing channels exploit information leakage between security domains that should be isolated, bypassing the operating system's security boundaries. These channels result from contention for shared microarchitectural…