Cryptography and Security (cs.CR)

Abstract: With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts to the model provider. Previous studies have studied secure inference for Transformer models using secure multiparty computation (MPC), where model parameters and clients' prompts are kept secret. Despite this, these frameworks are still limited in terms of model performance, efficiency, and deployment. To address these limitations, we propose framework PUMA to enable fast and secure Transformer model inference. Our framework designs high quality approximations for expensive functions, such as GeLU and Softmax, which significantly reduce the cost of secure inference while preserving the model performance. Additionally, we design secure Embedding and LayerNorm procedures that faithfully implement the desired functionality without undermining the Transformer architecture. PUMA is about 2x faster than the state-of-the-art MPC framework MPCFORMER(ICLR 2023) and has similar accuracy as plaintext models without fine-tuning (which the previous works failed to achieve). One more thing, PUMA can evaluate LLaMA-7B in around 5 minutes to generate 1 token. To our best knowledge, this is the first time that a model with such a parameter size is able to be evaluated under MPC. PUMA has been open-sourced in the Github repository of SecretFlow-SPU.

Abstract: RISC-V is a recently developed open instruction set architecture gaining a lot of attention. To achieve a lasting security on these systems and design efficient countermeasures, a better understanding of vulnerabilities to novel and potential future attacks is mandatory. This paper demonstrates that RISC-V is sensible to Jump-Oriented Programming, a class of complex code-reuse attacks. We provide an analysis of new dispatcher gadgets we discovered, and show how they can be used together in order to build a stealth attack, bypassing existing protections. A proof-of-concept attack is implemented on an embedded web server compiled for RISC-V, in which we introduced a vulnerability, allowing an attacker to remotely read an arbitrary file from the host machine.

Abstract: The rapid growth of decentralized digital currencies, enabled by blockchain technology, has ushered in a new era of peer-to-peer transactions, revolutionizing the global economy. Cryptocurrency wallets, serving as crucial endpoints for these transactions, have become increasingly prevalent. However, the escalating value and usage of these wallets also expose them to significant security risks and challenges. This research aims to comprehensively explore the security aspects of cryptocurrency wallets. It provides a taxonomy of wallet types, analyzes their design and implementation, identifies common vulnerabilities and attacks, and discusses defense mechanisms and mitigation strategies. The taxonomy covers custodial, non-custodial, hot, and cold wallets, highlighting their unique characteristics and associated security considerations. The security analysis scrutinizes the theoretical and practical aspects of wallet design, while assessing the efficacy of existing security measures and protocols. Notable wallet attacks, such as Binance, Mt. Gox are examined to understand their causes and consequences. Furthermore, the paper surveys defense mechanisms, transaction monitoring, evaluating their effectiveness in mitigating threats.