Related papers: When Mitigations Backfire: Timing Channel Attacks …
Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protecting their parameters is critical not only for maintaining a…
Smart jamming attacks on cellular campus networks represent an enormous potential threat, especially in the industrial environment. In complex production processes, the disruption of a single wireless connected Cyber-Physical System (CPS)…
In this paper we introduced countermeasures against side-channel attacks in the shared memory of TrustZone. We proposed zero-contention cache memory or policy between REE and TEE to prevent from TruSpy attacks in TrustZone. And we suggested…
Realizing flow security in a concurrent environment is extremely challenging, primarily due to non-deterministic nature of execution. The difficulty is further exacerbated from a security angle if sequential threads disclose control…
Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…
Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…
Our ISCA 2014 paper provided the first scientific and detailed characterization, analysis, and real-system demonstration of what is now popularly known as the RowHammer phenomenon (or vulnerability) in modern commodity DRAM chips, which are…
Modern processors dynamically control their operating frequency to optimize resource utilization, maximize energy savings, and conform to system-defined constraints. If, during the execution of a software workload, the running average of…
Side-channel and fault injection attacks reveal secret information by monitoring or manipulating the physical effects of computations involving secret variables. Circuit-level countermeasures help to deter these attacks, and traditionally…
The implementations of most hardened cryptographic libraries use defensive programming techniques for side-channel resistance. These techniques are usually specified as guidelines to developers on specific code patterns to use or avoid.…
Hardware caches are essential performance optimization features in modern processors to reduce the effective memory access time. Unfortunately, they are also the prime targets for attacks on computer processors because they are…
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation…
Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a knowledge graph. While Graph RAG improves relational…
The Open Radio Access Network (O-RAN) offers flexibility and innovation but introduces unique security vulnerabilities, particularly from cryptographically relevant quantum computers. While Post-Quantum Cryptography (PQC) is the primary…
Rowhammer attacks that corrupt level-1 page tables to gain kernel privilege are the most detrimental to system security and hard to mitigate. However, recently proposed software-only mitigations are not effective against such kernel…
Microarchitectural timing channels exploit information leakage between security domains that should be isolated, bypassing the operating system's security boundaries. These channels result from contention for shared microarchitectural…
Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused…
Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses attempt to reduce attack accuracy by disrupting traffic…
The code generation modules inside modern compilers such as GCC and LLVM, which use a limited number of CPU registers to store a large number of program variables, may introduce side-channel leaks even in software equipped with…
Retrieval-Augmented Generation (RAG) is essential for enhancing Large Language Models (LLMs) with external knowledge, but its reliance on cloud environments exposes sensitive data to privacy risks. Existing privacy-preserving solutions…