Related papers: Exploiting Behavioral Side-Channels in Observation…
Out-of-distribution (OOD) detection has received much attention lately due to its practical importance in enhancing the safe deployment of neural networks. One of the primary challenges is that models often produce highly confident…
In this short paper, we propose the split-diffuse (SD) algorithm that takes the output of an existing word embedding algorithm, and distributes the data points uniformly across the visualization space. The result improves the perceivability…
Smart wearable devices (SWDs) collect and store sensitive daily information of many people. Its primary method of identification is still the password unlocking method. However, several studies have shown serious security flaws in that…
Open-source software (OSS) is a critical component of modern software systems, yet supply chain security remains challenging in practice due to unavailable or obfuscated source code. Consequently, security teams often rely on runtime…
In cooperative ITS, security and privacy protection are essential. Cooperative Awareness Message (CAM) is a basic V2V message standard, and misbehavior detection is critical for protection against attacking CAMs from the inside system, in…
Monitoring the status of large computing systems is essential to identify unexpected behavior and improve their performance and uptime. However, due to the large-scale and distributed design of such computing systems as well as a large…
In multiagent systems (MASs), agents' observation upon system behaviours may improve the overall team performance, but may also leak sensitive information to an observer. A quantified observability analysis can thus be useful to assist…
Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-box attacks against the model. This paper presents the first…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Many Web Application Firewalls (WAFs) leverage the OWASP CRS to block incoming malicious requests. The CRS consists of different sets of rules designed by domain experts to detect well-known web attack patterns. Both the set of rules and…
An Intrusion Detection System (IDS) is a software that monitors a single or a network of computers for malicious activities (attacks) that are aimed at stealing or censoring information or corrupting network protocols. Most techniques used…
The widespread adoption of Reconfigurable Intelligent Surfaces (RISs) in future practical wireless systems is critically dependent on the integration of the RIS into higher-layer protocols beyond the physical (PHY) one, an issue that has…
As a kind of wavefront with helical phase, orbital angular momentum (OAM) shows the great potential to enhance the security results of wireless communications due to its unique orthogonality and central hollow electromagnetic wave…
In a spoofing attack, a malicious actor impersonates a legitimate user to access or manipulate data without authorization. The vulnerability of cryptographic security mechanisms to compromised user credentials motivates spoofing attack…
Online proctoring systems (OPS) are technologies and services that are used to monitor students during an online exam to deter cheating. However, OPS often violates student privacy by implementing overly intrusive surveillance to which…
Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…
Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…
Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel concepts. As these models gain traction in high-stakes…
High-latency anonymous communication systems prevent passive eavesdroppers from inferring communicating partners with certainty. However, disclosure attacks allow an adversary to recover users' behavioral profiles when communications are…
Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…