相关论文: Store-to-Leak Forwarding: Leaking Data on Meltdown…

Fault-injection attacks have been proven in the past to be a reliable way of bypassing hardware-based security measures, such as cryptographic hashes, privilege and access permission enforcement, and trusted execution environments. However,…

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…

Organizations use data lakes to store and analyze sensitive data. But hackers may compromise data lake storage to bypass access controls and access sensitive data. To address this, we propose Membrane, a system that (1) cryptographically…

Quantitative theories of information flow give us an approach to relax the absolute confidentiality properties that are difficult to satisfy for many practical programs. The classical information-theoretic approaches for sequential…

Control-flow leakage (CFL) attacks enable an attacker to expose control-flow decisions of a victim program via side-channel observations. Linearization (i.e., elimination) of secret-dependent control flow is the main countermeasure against…

A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or…

As large language models (LLMs) become more integral to society and technology, ensuring their safety becomes essential. Jailbreak attacks exploit vulnerabilities to bypass safety guardrails, posing a significant threat. However, the…

The Spectre speculative side-channel attacks pose formidable threats for security. Research has shown that code following the cryptographic constant-time discipline can be efficiently protected against Spectre v1 using a selective variant…

Besides cryptographic secrets, side-channel attacks also leak sensitive user input. The most accurate attacks exploit cache timings or interrupt information to monitor keystroke timings and subsequently infer typed words and sentences.…

Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible…

Caches are used to reduce the speed differential between the CPU and memory to improve the performance of modern processors. However, attackers can use contention-based cache timing attacks to steal sensitive information from victim…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

The exponential growth of internet connected systems has generated numerous challenges, such as spectrum shortage issues, which require efficient spectrum sharing (SS) solutions. Complicated and dynamic SS systems can be exposed to…

In this paper, we reveal the existence of a new class of prefetcher, the XPT prefetcher, in the modern Intel processors which has never been officially documented. It speculatively issues a load, bypassing last-level cache (LLC) lookups,…

Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as adversarial reconnaissance for an attacker. A systematic evaluation of prompt…

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

How to provide information security while fulfilling ultra reliability and low-latency requirements is one of the major concerns for enabling the next generation of ultra-reliable and low-latency communications service (xURLLC), specially…

Caches have been used to construct various types of covert and side channels to leak information. Most existing cache channels exploit the timing difference between cache hits and cache misses. However, we introduce a new and broader…

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks,…

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…