相关论文: SafeLLVM: LLVM Without The ROP Gadgets!

Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by…

The security of billions of devices worldwide depends on the security and robustness of the mainline Linux kernel. However, the increasing number of kernel-specific vulnerabilities, especially memory safety vulnerabilities, shows that the…

Unsafe memory accesses in programs written using popular programming languages like C/C++ have been among the leading causes for software vulnerability. Prior memory safety checkers such as SoftBound enforce memory spatial safety by…

Memory safety violations in low-level code, written in languages like C, continues to remain one of the major sources of software vulnerabilities. One method of removing such violations by construction is to port C code to a safe C dialect.…

Energy conservative devices are the need of the modern technology which leads to the development of reversible logic. The synthesis of reversible logic has become an intensely studied area as it overcomes the problem of power dissipation…

It is well known that encryption alone is not enough to protect data privacy. Access patterns, revealed when operations are performed, can also be leveraged in inference attacks. Oblivious RAM (ORAM) hides access patterns by making client…

Rowhammer has drawn much attention from both academia and industry in the past years as rowhammer exploitation poses severe consequences to system security. Since the first comprehensive study of rowhammer in 2014, a number of rowhammer…

LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence in LLM-generated software and introduce Feature--Security…

Applications with safety requirements have become ubiquitous nowadays and can be found in edge devices of all kinds. However, microcontrollers in those devices, despite offering moderate performance by implementing multicores and cache…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhances code security by integrating Retrieval-Augmented…

Universal Serial Bus (USB)-based attacks have increased in complexity in recent years. Modern attacks incorporate a wide range of attack vectors, from social engineering to signal injection. The security community is addressing these…

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…

Memory corruption vulnerabilities remain one of the most severe threats to software security. They often allow attackers to achieve arbitrary code execution by redirecting a vulnerable program's control flow. While Control Flow Integrity…

Nowadays, an increasing number of applications uses deserialization. This technique, based on rebuilding the instance of objects from serialized byte streams, can be dangerous since it can open the application to attacks such as remote code…

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But recent evidence shows that it can simultaneously degrade…

One reason for not adopting cloud services is the required trust in the cloud provider: As they control the hypervisor, any data processed in the system is accessible to them. Full memory encryption for Virtual Machines (VM) protects…

Heap memory errors remain a major source of software vulnerabilities. Existing memory safety defenses aim at protecting all objects, resulting in high performance cost and incomplete protection. Instead, we propose an approach that…

As large language models (LLMs) scale, their inference incurs substantial computational resources, exposing them to energy-latency attacks, where crafted prompts induce high energy and latency cost. Existing attack methods aim to prolong…

Memory corruption vulnerabilities in C/C++ applications enable attackers to execute code, change data, and leak information. Current memory sanitizers do no provide comprehensive coverage of a program's data. In particular, existing tools…