Related papers: Rethinking Broken Object Level Authorization Attac…
Securing critical assets in a bus-based System-On-Chip (SoC) is imperative to mitigate potential vulnerabilities and prevent unauthorized access, ensuring the integrity, availability, and confidentiality of the system. Ensuring security…
This paper introduces the Identity Control Plane (ICP), an architectural framework for enforcing identity-aware Zero Trust access across human users, workloads, and automation systems. The ICP model unifies SPIFFE-based workload identity,…
Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This…
Integrity checking is ubiquitous in data networks, but not all network traffic needs integrity protection. Many applications can tolerate slightly damaged data while still working acceptably, trading accuracy versus efficiency to save time…
Database as a service provides services for accessing and managing customers data which provides ease of access, and the cost is less for these services. There is a possibility that the DBaaS service provider may not be trusted, and data…
Vulnerability Discovery with attack Injection security threats are increasing for the server software, when software is developed, the software tested for the functionality. Due to unawareness of software vulnerabilities most of the…
Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…
Authentication and authorization are two key elements of a software application. In modern day, OAuth 2.0 framework and OpenID Connect protocol are widely adopted standards fulfilling these requirements. These protocols are implemented into…
Zero Trust Architecture (ZTA) has become a widely adopted model for securing enterprise environments, promoting continuous verification and minimal trust across systems. However, its application in mobile contexts remains limited, despite…
Hardware-software leakage contracts have emerged as a formalism for specifying side-channel security guarantees of modern processors, yet verifying that a complex hardware design complies with its contract remains a major challenge. While…
In the standard privacy-preserving Machine learning as-a-service (MLaaS) model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and tool backends. In such settings, reliability isno longer…
Java applications are prone to vulnerabilities stemming from the insecure use of security-sensitive APIs, such as file operations enabling path traversal or deserialization routines allowing remote code execution. These sink APIs encode…
AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…
Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches face two key limitations: (1) they overlook the critical…
The widespread adoption of cloud computing has resulted in the proliferation of open source cloud computing frameworks that give more control to enterprises over their data and networks. Though the benefits of open source software are…
Federated Learning (FL) is a novel client-server distributed learning framework that can protect data privacy. However, recent works show that FL is vulnerable to poisoning attacks. Many defenses with robust aggregators (AGRs) are proposed…
Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing…
Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In…