Greta Dolcetti, Giulio Zizzo, Sergio Maffeis
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure the effectiveness of eight different defences. Our results show how these models are not safe by default, and how the defences are not yet employable in real-world scenarios.
Greta Dolcetti, Vincenzo Arceri, Eleonora Iotti et al.
Large Language Models (LLMs) are one of the most promising developments in the field of artificial intelligence, and the software engineering community has readily noticed their potential role in the software development life-cycle. Developers routinely ask LLMs to generate code snippets, increasing productivity but also potentially introducing ownership, privacy, correctness, and security issues. Previous work highlighted how code generated by mainstream commercial LLMs is often not safe, containing vulnerabilities, bugs, and code smells. In this paper, we present a framework that leverages testing and static analysis to assess the quality, and guide the self-improvement, of code generated by general-purpose, open-source LLMs. First, we ask LLMs to generate C code to solve a number of programming tasks. Then we employ ground-truth tests to assess the (in)correctness of the generated code, and a static analysis tool to detect potential safety vulnerabilities. Next, we assess the models ability to evaluate the generated code, by asking them to detect errors and vulnerabilities. Finally, we test the models ability to fix the generated code, providing the reports produced during the static analysis and incorrectness evaluation phases as feedback. Our results show that models often produce incorrect code, and that the generated code can include safety issues. Moreover, they perform very poorly at detecting either issue. On the positive side, we observe a substantial ability to fix flawed code when provided with information about failed tests or potential vulnerabilities, indicating a promising avenue for improving the safety of LLM-based code generation tools.
Alessandro De Palma, Greta Dolcetti, Caterina Urban
Verified explanations are a theoretically-principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifier-optimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations.