Related papers: SafeLLVM: LLVM Without The ROP Gadgets!

Software supply-chain attacks are an important and ongoing concern in the open source software ecosystem. These attacks maintain the standard functionality that a component implements, but additionally hide malicious functionality activated…

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

In today's digital age, the ease of data collection, transfer, and storage continue to shape modern society and the ways we interact with our world. The advantages are numerous, but there is also an increased risk of information…

Although the integration of large language models (LLMs) into robotics has unlocked transformative capabilities, it has also introduced significant safety concerns, ranging from average-case LLM errors (e.g., hallucinations) to adversarial…

The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security challenges, as LLM-generated code often contains…

This retrospective paper describes the RowHammer problem in Dynamic Random Access Memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 conference~\cite{rowhammer-isca2014}. RowHammer is a prime (and perhaps the…

Modern operating systems manage and abstract hardware resources, to ensure efficient execution of user workloads. The operating system must securely interface with often untrusted user code while relying on hardware that is assumed to be…

Modern CPU architectures offer strong isolation guarantees towards user applications in the form of enclaves. For instance, Intel's threat model for SGX assumes fully trusted enclaves, yet there is an ongoing debate on whether this threat…

In spite of years of improvements to software security, heap-related attacks still remain a severe threat. One reason is that many existing memory allocators fall short in a variety of aspects. For instance, performance-oriented allocators…

Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have gained significant attention due to their objective and verifiable reward signals, demonstrating strong performance in reasoning and code generation tasks.…

Address Space Layout Randomization (ASLR) is one of the most prominently deployed mitigations against memory corruption attacks. ASLR randomly shuffles program virtual addresses to prevent attackers from knowing the location of program…

Nowadays most of the malware applications are either packed or protected. This techniques are applied especially to evade signature based detectors and also to complicate the job of reverse engineers or security analysts. The time one must…

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,…

Logic Encryption is one of the most popular hardware security techniques which can prevent IP piracy and illegal IC overproduction. It introduces obfuscation by inserting some extra hardware into a design to hide its functionality from…

While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text. Existing defensive…

We live in a world where our personal data are both valuable and vulnerable to misappropriation through exploitation of security vulnerabilities in online services. For instance, Dropbox, a popular cloud storage tool, has certain security…

Existing anti-malware software and reverse engineering toolkits struggle with stealthy sub-OS rootkits due to limitations of run-time kernel-level monitoring. A malicious kernel-level driver can bypass OS-level anti-virus mechanisms easily.…