相关论文: Resolving the Correct Library: A Loader-Level Defe…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their…

Due to the rise of the Internet of Things, there are many new chips and platforms available for hobbyists and industry alike to build smart devices. The SDKs for these new platforms usually include closed-source binaries containing wireless…

Similar to a strategic interaction between rational and intelligent agents, cryptography problems can be examined through the prism of game theory. In this setting, the agent aiming to protect a message is called the defender, while the one…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

In federated learning, multiple parties collaborate in order to train a global model over their respective datasets. Even though cryptographic primitives (e.g., homomorphic encryption) can help achieve data privacy in this setting, some…

Malicious attacks on open-source software packages are a growing concern. The discovery of the XZ Utils backdoor intensified these concerns because of the potential widespread impact. This study, therefore, explores the challenges of…

Distributed deep learning frameworks such as split learning provide great benefits with regards to the computational cost of training deep neural networks and the privacy-aware utilization of the collective data of a group of data-holders.…

Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigram, and DipMark, derive their security guarantees from the assumption that the underlying…

Virtualization enables information and communications technology industry to better manage computing resources. In this regard, improvements in virtualization approaches together with the need for consistent runtime environment, lower…

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…

Control Flow Hijacking attacks have posed a serious threat to the security of applications for a long time where an attacker can damage the control Flow Integrity of the program and execute arbitrary code. These attacks can be performed by…

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…

Binary program analysis represents a fundamental pillar of modern system security. Fine-grained methodologies like dynamic taint analysis still suffer from deployment complexity and performance overhead despite significant progress.…

Software supply-chain attacks are an important and ongoing concern in the open source software ecosystem. These attacks maintain the standard functionality that a component implements, but additionally hide malicious functionality activated…

This study investigates the potential of WebAssembly as a more secure and efficient alternative to Linux containers for executing untrusted code in cloud computing with Kubernetes. Specifically, it evaluates the security and performance…

Containerization has emerged as a revolutionary technology in the software development and deployment industry. Containers offer a portable and lightweight solution that allows for packaging applications and their dependencies…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…