相关论文: "It's a Trap!"-How Speculation Invariance Can Be A…

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or…

Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess…

Information leakage is a significant problem in modern software systems. Information leaks due to side channels are especially hard to detect and analyze. In this paper, we present techniques for automated synthesis of adaptive side-channel…

To meet the ever-growing need for performance in silicon devices, SoC providers have been increasingly relying on software-hardware cooperation. By controlling hardware resources such as power or clock management from the software,…

We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data, such as missing or noisy variables. Our approach builds on conformal prediction, a powerful framework to…

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.…

Side channels represent a broad class of security vulnerabilities that have been demonstrated to exist in many applications. Because completely eliminating side channels often leads to prohibitively high overhead, there is a need for a…

Several randomization mechanisms for local differential privacy (LDP) (e.g., randomized response) are well-studied to improve the utility. However, recent studies show that LDP is generally vulnerable to malicious data providers in nature.…

Secure applications implement software protections against side-channel and physical attacks. Such protections are meaningful at machine code or micro-architectural level, but they typically do not carry observable semantics at source…

We present a family of gossiping algorithms whose members share the same structure though they vary their performance in function of a combinatorial parameter. We show that such parameter may be considered as a "knob" controlling the amount…

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…

AI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result in the unintended leakage of private information to external parties. We propose…

Large-scale online service platforms face severe challenges from organized platform abuse: multiple forms such as credit card fraud and promotion abuse continually emerge, characterized by large numbers of involved accounts, rapid…

Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…

We propose the concept of Speculative Execution for Visual Analytics and discuss its effectiveness for model exploration and optimization. Speculative Execution enables the automatic generation of alternative, competing model configurations…

Since the discovery of Spectre, a large number of hardware mechanisms for secure speculation has been proposed. Intuitively, more defensive mechanisms are less efficient but can securely execute a larger class of programs, while more…

Side-channel attacks have become prominent attack surfaces in cyberspace. Attackers use the side information generated by the system while performing a task. Among the various side-channel attacks, cache side-channel attacks are leading as…

Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach for detecting timing side channels, it is computationally…

We propose an operational measure of information leakage in a non-stochastic setting to formalize privacy against a brute-force guessing adversary. We use uncertain variables, non-probabilistic counterparts of random variables, to construct…