相关论文: Retrofitting Fine Grain Isolation in the Firefox R…
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the…
Testing ultra-large microservices-based FinTech systems presents significant challenges, including restricted access to production environments, complex dependencies, and stringent security constraints. We propose SandBoxFuzz, a scalable…
Modern software development is increasingly dependent on components, libraries and frameworks coming from third-party vendors or open-source suppliers and made available through a number of platforms (or forges). This way of writing…
Reverse engineering (RE) of x86 binaries is indispensable for malware and firmware analysis, but remains slow due to stripped metadata and adversarial obfuscation. Large Language Models (LLMs) offer potential for improving RE efficiency…
In the quest for efficiency and performance, edge-computing providers eliminate isolation boundaries between tenants, such as strict process isolation, and instead let them compute in a more lightweight multi-threaded single-process design.…
We present a new hierarchical compression scheme for encoding light field images (LFI) that is suitable for interactive rendering. Our method (RLFC) exploits redundancies in the light field images by constructing a tree structure. The top…
Software based fault isolation (SFI) is a powerful approach to reduce the impact of security vulnerabilities in large C/C++ applications like Firefox and Apache. Unfortunately, practical SFI tools have not been broadly available. Developing…
Even todays most advanced machine learning models are easily fooled by almost imperceptible perturbations of their inputs. Foolbox is a new Python package to generate such adversarial perturbations and to quantify and compare the robustness…
We develop a framework for efficiently transforming certain approximation algorithms into differentially-private variants, in a black-box manner. Specifically, our results focus on algorithms A that output an approximation to a function f…
Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…
Isolating programs is an important mechanism to support more secure applications. Isolating program in dynamic languages such as JavaScript is even more challenging since reflective operations can circumvent simple mechanisms that could…
The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e.g., image captioning, VQA). Despite the tremendous progress in visual…
Be it for a malicious or legitimate purpose, packing, a transformation that consists in applying various operations like compression or encryption to a binary file, i.e. for making reverse engineering harder or obfuscating code, is widely…
Many applications have service requirements that are not easily met by existing operating systems. Real-time and security-critical tasks, for example, often require custom OSes to meet their needs. However, development of special purpose…
With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…
Context. White-box test generation is a technique used for automatically selecting test inputs using only the source or binary code. However, such techniques encounter challenges when applying them to complex programs. One of the main…
Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this…
This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level…
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…
Large Language Models (LLMs) are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial…