Related papers: Towards automated web application logic reconstruc…

Classic firewall systems are built to filter traffic based on IP addresses, source and destination ports and protocol types. The modern networks have grown to a level where the possibility for users' mobility is a must. In such networks,…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Application Programming Interface (API) Injection attacks refer to the unauthorized or malicious use of APIs, which are often exploited to gain access to sensitive data or manipulate online systems for illicit purposes. Identifying actors…

Automated cyber threat detection in computer networks is a major challenge in cybersecurity. The cyber domain has inherent challenges that make traditional machine learning techniques problematic, specifically the need to learn continually…

Organizations face an ever-changing threat landscape. They must continuously dedicate significant efforts to protect their assets, making their adoption of increased cybersecurity automation inevitable. However, process automation requires…

Webshell attacks are becoming more common, requiring robust detection mechanisms to protect web applications. The dissertation clearly states two research directions: scanning web application source code and analyzing HTTP traffic to detect…

This work addresses JavaScript malware detection to enhance client-side web application security with a behavior-based system. The ability to detect malicious JavaScript execution sequences is a critical problem in modern web security as…

The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…

Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

While machine learning is vulnerable to adversarial examples, it still lacks systematic procedures and tools for evaluating its security in different application contexts. In this article, we discuss how to develop automated and scalable…

With web applications becoming a preferred method of presenting graphical user interfaces to users, software vulnerabilities affecting web applications are becoming more and more prevalent and devastating. Some of these vulnerabilities,…

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…

Cloud computing environments are increasingly vulnerable to security threats such as distributed denial-of-service (DDoS) attacks and SQL injection. Traditional security mechanisms, based on rule matching and feature recognition, struggle…

Web applications are becoming more ubiquitous. All manner of physical devices are now connected and often have a variety of web applications and web-interfaces. This proliferation of web applications has been accompanied by an increase in…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Face anti-spoofing aims to discriminate the spoofing face images (e.g., printed photos) from live ones. However, adversarial examples greatly challenge its credibility, where adding some perturbation noise can easily change the predictions.…

Typical design flows are hierarchical and rely on assembling many individual technology elements from standard cells to complete boards. Providers use compact models to provide simplified views of their products to their users. Designers…

Carriage return (CR) and line feed (LF), also known as CRLF injection is a type of vulnerability that allows a hacker to enter special characters into a web application, altering its operation or confusing the administrator. Log poisoning…

Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit…