Related papers: Pitfalls in Designing Zero-Effort Deauthentication…
Activation monitoring, which probes a model's internal states using lightweight classifiers, is an emerging tool for AI safety. However, its worst-case robustness under a misalignment threat model--where a model might learn to actively…
This paper describes a baseline for the second iteration of the Fact Extraction and VERification shared task (FEVER2.0) which explores the resilience of systems through adversarial evaluation. We present a collection of simple adversarial…
Continuous authentication has been proposed as a complementary security mechanism to password-based authentication for computer devices that are handled directly by humans, such as smart phones. Continuous authentication has some privacy…
In this paper we discuss the difficulties of mounting successful attack against crypto implementations when essential information is missing. We start with a detailed description of our attack against our own design, to highlight which…
While DeepFake applications are becoming popular in recent years, their abuses pose a serious privacy threat. Unfortunately, most related detection algorithms to mitigate the abuse issues are inherently vulnerable to adversarial attacks…
Web password recovery, enabling a user who forgets their password to re-establish a shared secret with a website, is very widely implemented. However, use of such a fall-back system brings with it additional vulnerabilities to user…
Face recognition (FR) systems have demonstrated outstanding verification performance, suggesting suitability for real-world applications ranging from photo tagging in social media to automated border control (ABC). In an advanced FR system…
Security attacks are growing in an exponential manner and their impact on existing systems is seriously high and can lead to dangerous consequences. However, in order to reduce the effect of these attacks, penetration tests are highly…
Machine unlearning, where users can request the deletion of a forget dataset, is becoming increasingly important because of numerous privacy regulations. Initial works on ``exact'' unlearning (e.g., retraining) incur large computational…
In this paper, we study the probability of successful deception of an uncompressed biometric authentication system with side information at the adversary. It represents the scenario where the adversary may have correlated side information,…
Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…
Evaluating the effectiveness of software protection is crucial for selecting the most effective methods to safeguard assets within software applications. Obfuscation involves techniques that deliberately modify software to make it more…
The massive explosion and ubiquity of computing devices and the outreach of the web have been the most defining events of the century so far. As more and more people gain access to the internet, traditional know-something and have-something…
In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…
Introduced by Juels and Rivest in 2013, Honeywords, which are decoy passwords stored alongside a real password, appear to be a proactive method to help detect password credentials misuse. However, despite over a decade of research, this…
Individuals lack oversight over systems that process their data. This can lead to discrimination and hidden biases that are hard to uncover. Recent data protection legislation tries to tackle these issues, but it is inadequate. It does not…
Password-based authentication faces various security and usability issues. Password managers help alleviate some of these issues by enabling users to manage their passwords effectively. However, malicious client-side scripts and browser…
Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant…
Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…
Intention deception involves computing a strategy which deceives the opponent into a wrong belief about the agent's intention or objective. This paper studies a class of probabilistic planning problems with intention deception and…