Related papers: IFCIL: An Information Flow Configuration Language …
Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples…
It is common to prove by reasoning over source code that programs do not leak sensitive data. But doing so leaves a gap between reasoning and reality that can only be filled by accounting for the behaviour of the compiler. This task is…
Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of vulnerabilities that only manifest under specific option-input combinations. Prior works of CLI…
Developers and data scientists often struggle to write command-line inputs, even though graphical interfaces or tools like ChatGPT can assist. The solution? "ai-cli," an open-source system inspired by GitHub Copilot that converts natural…
This paper presents LWeb, a framework for enforcing label-based, information flow policies in database-using web applications. In a nutshell, LWeb marries the LIO Haskell IFC enforcement library with the Yesod web programming framework. The…
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…
As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…
Websites today routinely combine JavaScript from multiple sources, both trusted and untrusted. Hence, JavaScript security is of paramount importance. A specific interesting problem is information flow control (IFC) for JavaScript. In this…
Reified Input/Output (I/O) logic[21] has been recently proposed to model real-world norms in terms of the logic in [11]. This is massively grounded on the notion of reification, and it has specifically designed to model meaning of natural…
SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…
Programming modern high-performance computing systems is challenging due to the need to efficiently program GPUs and accelerators and to handle data movement between nodes. The C++ language has been continuously enhanced in recent years…
Assured Remote Execution on a device is the ability of suitably authorized parties to construct secure channels with known processes -- i.e. processes executing known code -- running on it. Assured Remote Execution requires a hardware basis…
Built on top of UDP, the relatively new QUIC protocol serves as the baseline for modern web protocol stacks. Equipped with a rich feature set, the protocol is defined by a 151 pages strong IETF standard complemented by several additional…
Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…
Context and motivation: Usage of Formal Specification languages is scarce in web application development as compared to safety critical/hardware systems. Question/problem: An apt formal specification language should provide the following…
As an emerging application paradigm, serverless computing attracts attention from more and more attackers. Unfortunately, security tools for conventional applications cannot be easily ported to serverless, and existing serverless security…
Symbolic execution has always been plagued by the inability to handle programs that require highly structured inputs. Most often, the symbolic execution engine gets overwhelmed by the sheer number of infeasible paths and fails to explore…
The growing sophistication, frequency, and diversity of cyberattacks increasingly exceed the capacity of individual entities to fully understand and counter them. While existing solutions, such as Security Information and Event Management…
Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling…