Related papers: Automatically Eliminating Speculative Leaks from C…
To combat the memory bandwidth-bound nature of autoregressive LLM inference, previous research has proposed the speculative decoding frame-work. To perform speculative decoding, a small draft model proposes candidate continuations of the…
Control Flow Graphs are one of the main data sources for software analysis that use dynamic and static software analysis methods. Protected software and modern malware increasingly depend on dynamic code loading techniques to evade static…
Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads and system-level constraints. We present TIDE (Temporal Incremental Draft Engine), a…
Out-of-order execution and speculative execution are among the biggest contributors to performance and efficiency of modern processors. However, they are inconsiderate, leaking secret data during the transient execution of instructions.…
Modern microarchitectures incorporate optimization techniques such as speculative loads and store forwarding to improve the memory bottleneck. The processor executes the load speculatively before the stores, and forwards the data of a…
The application of Large Language Models (LLMs) for Automated Algorithm Discovery (AAD), particularly for optimisation heuristics, is an emerging field of research. This emergence necessitates robust, standardised benchmarking practices to…
Certified deletion ensures that encrypted data can be irreversibly deleted, preventing future recovery even if decryption keys are later exposed. Although existing works have achieved certified deletion across various cryptographic…
Speculative execution is crucial in enhancing modern processor performance but can introduce Spectre-type vulnerabilities that may leak sensitive information. Detecting Spectre gadgets from programs has been a research focus to enhance the…
The disclosure of the Spectre speculative-execution attacks in January 2018 has left a severe vulnerability that systems are still struggling with how to patch. The solutions that currently exist tend to have incomplete coverage, perform…
Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…
Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…
Leakage contracts have recently been proposed as a new security abstraction at the Instruction Set Architecture (ISA) level. Such contracts aim to faithfully capture the information processors may leak through side effects of their…
This paper provides the first systematic analysis of a synergistic threat model encompassing memory corruption vulnerabilities and microarchitectural side-channel vulnerabilities. We study speculative shield bypass attacks that leverage…
Whenever modern CPUs encounter a conditional branch for which the condition cannot be evaluated yet, they predict the likely branch target and speculatively execute code. Such pipelining is key to optimizing runtime performance and is…
While the reliable use of some NP-complete problem in tandem with the assumption that P is not equal to NP has eluded cryptographers due to lack of results showing average-case hardness, one alternative which has been explored is reliance…
Soft errors are a type of transient digital signal corruption that occurs in digital hardware components such as the internal flip-flops of CPU pipelines, the register file, memory cells, and even internal communication buses. Soft errors…
We consider the problem of specifying and proving the security of non-trivial, concurrent programs that intentionally leak information. We present a method that decomposes the problem into (a) proving that the program only leaks information…
We propose a novel approach to improving software security called Cryptographic Path Hardening, which is aimed at hiding security vulnerabilities in software from attackers through the use of provably secure and obfuscated cryptographic…
Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…
Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results…