相关论文: ScrambleSuit: A Polymorph Network Protocol to Circ…
In a hostile network environment, users must communicate without being detected. This involves blending in with the existing traffic. In some cases, a higher degree of secrecy is required. We present a proof-of-concept format transforming…
The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…
Nodes in route-restricted overlays have an immutable set of neighbors, explicitly specified by their users. Popular examples include payment networks such as the Lightning network as well as social overlays such as the Dark Freenet. Routing…
Be it for a malicious or legitimate purpose, packing, a transformation that consists in applying various operations like compression or encryption to a binary file, i.e. for making reverse engineering harder or obfuscating code, is widely…
The era of widespread globalization has led to the emergence of hardware-centric security threats throughout the IC supply chain. Prior defenses like logic locking, layout camouflaging, and split manufacturing have been researched…
Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…
Covert channels can be used to circumvent system and network policies by establishing communications that have not been considered in the design of the computing system. We construct a covert channel between different computing systems that…
Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse…
Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-based image generation and editing techniques poses a new…
Finding a suitable data representation for a specific task has been shown to be crucial in many applications. The success of subspace clustering depends on the assumption that the data can be separated into different subspaces. However,…
Website fingerprinting attacks enable an adversary to infer which website a victim is visiting, even if the victim uses an encrypting proxy, such as Tor. Previous work has shown that all proposed defenses against website fingerprinting…
In its current state, the Internet does not provide end users with transparency and control regarding on-path forwarding devices. In particular, the lack of network device information reduces the trustworthiness of the forwarding path and…
Existing anti-malware software and reverse engineering toolkits struggle with stealthy sub-OS rootkits due to limitations of run-time kernel-level monitoring. A malicious kernel-level driver can bypass OS-level anti-virus mechanisms easily.…
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the…
Manipulation tools that realistically edit images are widely available, making it easy for anyone to create and spread misinformation. In an attempt to fight fake news, forgery detection and localization methods were designed. However,…
The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion detection systems. This work presents SecureScan, an AI-driven, triple-layer detection framework…
Since training a deep neural network (DNN) is costly, the well-trained deep models can be regarded as valuable intellectual property (IP) assets. The IP protection associated with deep models has been receiving increasing attentions in…
Computational capability often falls short when confronted with massive data, posing a common challenge in establishing a statistical model or statistical inference method dealing with big data. While subsampling techniques have been…
Today's distributed network control planes support multiple routing protocols, filtering mechanisms, and route selection policies. These protocols operate at different layers, e.g. BGP operates at the EGP layer, OSPF at the IGP layer, and…
Recent work, motivated by anonymous messaging platforms, has introduced adaptive diffusion protocols which can obfuscate the source of a rumor: a "snapshot adversary" with access to the subgraph of "infected" nodes can do no better than…