Related papers: A Secure Design Pattern Approach Toward Tackling L…

Side-channel attacks have become a severe threat to the confidentiality of computer applications and systems. One popular type of such attacks is the microarchitectural attack, where the adversary exploits the hardware features to break the…

Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it difficult for the…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural…

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks,…

Users are demanding increased data security. As a result, security is rapidly becoming a first-order design constraint in next generation computing systems. Researchers and practitioners are exploring various security technologies to meet…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Speculative execution attacks undermine the security of constant-time programming, the standard technique used to prevent microarchitectural side channels in security-sensitive software such as cryptographic code. Constant-time code must…

Reactive injection attacks are a class of security threats in wireless networks wherein adversaries opportunistically inject spoofing packets in the frequency band of a client thereby forcing the base-station to deploy…

We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…

Security is an important quality of software systems, but there is a huge lack of security experts. To overcome this gap, we aim to make security design knowledge reusable for architects by proposing the SecuRe recommendation approach to…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

The design of the defenses Internet systems can deploy against attack, especially adaptive and resilient defenses, must start from a realistic model of the threat. This requires an assessment of the capabilities of the adversary. The design…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges…

As Large Language Models (LLMs) become increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…