Related papers: SandBlaster: Reversing the Apple Sandbox
The rapid evolution of Large Language Models (LLMs) has unlocked new possibilities for applying artificial intelligence across a wide range of fields, including privacy engineering. As modern applications increasingly handle sensitive user…
Password managers help users more effectively manage their passwords, encouraging them to adopt stronger passwords across their many accounts. In contrast to desktop systems where password managers receive no system-level support, mobile…
Vetting security impacts introduced by third-party libraries in iOS apps requires a reliable library detection technique. Especially when a new vulnerability (or a privacy-invasive behavior) was discovered in a third-party library, there is…
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…
While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with executing untrusted…
Bluetooth is one of the most established technologies for short range digital wireless data transmission. With the advent of wearables and the Internet of Things (IoT), Bluetooth has again gained importance, which makes security research…
Clustering has been well studied for desktop malware analysis as an effective triage method. Conventional similarity-based clustering techniques, however, cannot be immediately applied to Android malware analysis due to the excessive use of…
Deep learning is a powerful weapon to boost application performance in many fields, including face recognition, object detection, image classification, natural language understanding, and recommendation system. With the rapid increase in…
Behavioral data generated by users' devices, ranging from emoji use to pages visited, are collected at scale to improve apps and services. These data, however, contain fine-grained records and can reveal sensitive information about…
Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and targeted backdoor attacks. Mitigating such vulnerabilities…
The widespread use of smartphones in daily life has raised concerns about privacy and security among researchers and practitioners. Privacy issues are generally highly prevalent in mobile applications, particularly targeting the Android…
Mobile code presents a number of threats to machines that execute it. We introduce an approach for protecting machines and the resources they hold from mobile code, and describe a system based on our approach for protecting host machines…
Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…
Users need to configure default apps when they first start using their devices. The privacy configurations of the default apps do not always match what users think they have initially enabled. We first systematically evaluated the privacy…
Backdoor attack is a new AI security risk that has emerged in recent years. Drawing on the previous research of adversarial attack, we argue that the backdoor attack has the potential to tap into the model learning process and improve model…
Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy (DP). Apple's DifferentialPrivacy framework is deployed across its operating systems and handles sensitive…
Our objective is to protect the integrity and confidentiality of applications operating in untrusted environments. Trusted Execution Environments (TEEs) are not a panacea. Hardware TEEs fail to protect applications against Sybil, Fork and…
The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…
WebAssembly is revolutionizing the approach to developing modern applications. Although this technology was born to create portable and performant modules in web browsers, currently, its capabilities are extensively exploited in multiple…
There is a growing privacy concern due to the popularity of social media and surveillance systems, along with advances in face recognition software. However, established image obfuscation techniques are either vulnerable to…