相关论文: Exploiting Behavioral Side-Channels in Observation…

We describe a shared control methodology that can, without knowledge of the task, be used to improve a human's control of a dynamic system, be used as a training mechanism, and be used in conjunction with Imitation Learning to generate…

As the Internet of Things (IoT) continues to evolve, smartphones have become essential components of IoT systems. However, with the increasing amount of personal information stored on smartphones, user privacy is at risk of being…

Temporal action segmentation is typically achieved by discovering the dramatic variances in global visual descriptors. In this paper, we explore the merits of local features by proposing the unsupervised framework of Object-centric Temporal…

In this paper, we investigate physical-layer security for a heterogeneous cellular network consisting of a macro cell and a small cell in the presence of a passive eavesdropper that intends to tap both the macro-cell and small-cell…

Searchable Symmetric Encryption (SSE) allows a data owner to securely outsource its encrypted data to a cloud server while maintaining the ability to search over it and retrieve matched documents. Most existing SSE schemes leak which…

Cyber-attacks keep threatening global networks and information infrastructures. The threat is getting more and more destructive and hard to counter day by day as the global networks continue to enlarge exponentially with limited security…

Side Channel Analysis (SCA) presents a clear threat to privacy and security in modern computing systems. The vast majority of communications are secured through cryptographic algorithms. These algorithms are often provably-secure from a…

Advanced Driver-Assistance Systems (ADAS) have been attracting attention from many researchers. Vision-based sensors are the closest way to emulate human driver visual behavior while driving. In this paper, we explore possible ways to use…

This work mainly addresses continuous-time multiagent consensus networks where an adverse attacker affects the convergence performances of said protocol. In particular, we develop a novel secure-by-design approach in which the presence of a…

Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods like Cross-Stitch and Sluice network learn a linear…

Despite significant advancements in out-of-distribution (OOD) detection, existing methods still struggle to maintain robustness against adversarial attacks, compromising their reliability in critical real-world applications. Previous…

Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trusted hardware can keep this data private, but struggles to scale with a growing…

Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable…

Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning…

Security remains a critical challenge in modern web applications, where threats such as unauthorized access, data breaches, and injection attacks continue to undermine trust and reliability. Traditional Object-Oriented Programming (OOP)…

The STAR architecture was designed to test the value of the full Selective Tuning model of visual attention for complex real-world visuospatial tasks and behaviors. However, knowledge of how humans solve such tasks in 3D as active observers…

Machine learning has become mainstream across industries. Numerous examples proved the validity of it for security applications. In this work, we investigate how to reverse engineer a neural network by using only power side-channel…

Deep learning models are vulnerable to adversarial examples. As a more threatening type for practical deep learning systems, physical adversarial examples have received extensive research attention in recent years. However, without…

We show that Web and Research Agents (WRAs) -- language-model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive network observers. Deployment of WRAs \emph{locally} by…

Autonomous agents for cyber applications take advantage of modern defense techniques by adopting intelligent agents with conventional and learning-enabled components. These intelligent agents are trained via reinforcement learning (RL)…