Related papers: FIRST: FrontrunnIng Resilient Smart ConTracts
In this paper, we propose a groundbreaking quantum-secure federated learning (QFL) framework designed to safeguard distributed learning systems against the emerging threat of quantum-enabled adversaries. As classical cryptographic methods…
Blockchains have revolutionized decentralized applications, with composability enabling atomic, trustless interactions across smart contracts. However, layer 2 (L2) scalability solutions like rollups introduce fragmentation and hinder…
Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for…
Since the inception of Bitcoin, the distributed systems community has shown interest in the design of efficient blockchain systems. However, initial blockchain applications (like Bitcoin) attain very low throughput, which has promoted the…
With the improvements in computing technologies, edge devices in the Internet-of-Things have become more complex. The enabler technology for these complex systems are powerful application core processors with operating system support, such…
Federated learning (FL) enables collaborative model training across distributed clients while preserving data locality. Although FedAvg pioneered synchronous rounds for global model averaging, slower devices can delay collective progress.…
Price manipulation attack is one of the notorious threats in decentralized finance (DeFi) applications, which allows attackers to exchange tokens at an extensively deviated price from the market. Existing efforts usually rely on reactive…
In this study, we present a secure smart contract-based Verifiable Random Function (VRF) model, addressing the shortcomings of existing systems. As quantum computing emerges, conventional public key cryptography faces potential…
This paper contributes a formal framework for quantitative analysis of bounded sensor attacks on cyber-physical systems, using the formalism of differential dynamic logic. Given a precondition and postcondition of a system, we formalize two…
Blockchain technology transformed the digital sphere by providing a transparent, secure, and decentralized platform for data security across a range of industries, including cryptocurrencies and supply chain management. Blockchain's…
Federated Learning (FL) enables decentralized model training while preserving privacy. Recently, the integration of Foundation Models (FMs) into FL has enhanced performance but introduced a novel backdoor attack mechanism. Attackers can…
A frustratingly easy technique known as the prefilling attack has been shown to effectively circumvent the safety alignment of frontier LLMs by simply prefilling the assistant response with an affirmative prefix before decoding. In…
Cryptography often considers the strongest yet plausible attacks in the real world. Preprocessing (a.k.a. non-uniform attack) plays an important role in both theory and practice: an efficient online attacker can take advantage of advice…
We put forward the idea that classical blockchains and smart contracts are potentially useful primitives not only for classical cryptography, but for quantum cryptography as well. Abstractly, a smart contract is a functionality that allows…
AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…
The rapid advancement of open-source foundation models has brought transparency and accessibility to this groundbreaking technology. However, this openness has also enabled the development of highly-capable, unsafe models, as exemplified by…
Many researchers have proposed replacing the aggregation server in federated learning with a blockchain system to improve privacy, robustness, and scalability. In this approach, clients would upload their updated models to the blockchain…
Physically Unclonable Functions (PUFs) provide promising hardware security for IoT authentication, leveraging inherent randomness suitable for resource constrained environments. However, ML/DL modeling attacks threaten PUF security by…
Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model…
Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful…