相关论文: A Language-Based Approach for Improving the Robust…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters have not been sufficiently analyzed to understand if PEFT…

The Language Server Protocol (LSP) changed the field of Integrated Development Environments(IDEs), as it decouples core (programming) language features functionality from editor smarts, thus lowering the effort required to extend an IDE to…

Safety- and security-critical systems have to be thoroughly tested against their specifications. The state of practice is to have _natural language_ specifications, from which test cases are derived manually - a process that is slow,…

Today's datacenter applications rely on datastores that are required to provide high availability, consistency, and performance. To achieve high availability, these datastores replicate data across several nodes. Such replication is managed…

Reconfiguring the network stack allows applications to specialize the implementations of communication libraries depending on where they run, the requests they serve, and the performance they need to provide. Specializing applications in…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, where the natural language prompt plays a crucial role in conveying user intent to the model. However, prior studies have shown that LLMs are highly…

We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints. Our approach learns a selector to identify words…

Context: Reactive programming (RP) is a declarative programming paradigm suitable for expressing the handling of events. It enables programmers to create applications that react automatically to changes over time. Whenever a time-varying…

Traditionally, wireless network protocols have been designed for performance. Subsequently, as attacks have been identified, patches have been developed. This has resulted in an "arms race" development process of discovering vulnerabilities…

Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against adversarial…

This paper introduces a domain-specific Large Language Model for nuclear applications, built from the publicly accessible Essential CANDU textbook. Drawing on a compact Transformer-based architecture, the model is trained on a single GPU to…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Over the past decade, the automated generation of test inputs has made significant advances. Modern fuzzers and test generators easily produce complex input formats that do systematically cover the input and execution space. Testing…

Compression algorithms reduce the redundancy in data representation to decrease the storage required for that data. Data compression offers an attractive approach to reducing communication costs by using available bandwidth effectively.…

Robust modules guarantee to do only what they are supposed to do - even in the presence of untrusted, malicious clients, and considering not just the direct behaviour of individual methods, but also the emergent behaviour from calls to more…

Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions,…

In the area of networks, a common method to enforce a security policy expressed in a high-level language is based on an ad-hoc and manual rewriting process. We argue that it is possible to build a formal link between concrete and abstract…

Network protocol parsers are essential for enabling correct and secure communication between devices. Bugs in these parsers can introduce critical vulnerabilities, including memory corruption, information leakage, and denial-of-service…

Detecting vulnerabilities in software is a critical challenge in the development and deployment of applications. One of the most known and dangerous vulnerabilities is stack-based buffer overflows, which may allow potential attackers to…