Related papers: Protocol Dialects as Formal Patterns: A Composable…
Low-dimensional topological objects, such as knots and braids, have become prevalent in multiple areas of physics, such as fluid dynamics, optics, and quantum information processing. Such objects also now play a role in cryptography, where…
Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…
To take full advantage of a specific hardware target, performance engineers need to gain control on compilers in order to leverage their domain knowledge about the program and hardware. Yet, modern compilers are poorly controlled, usually…
Syntax connects words to each other in very specific ways. Two words are syntactically connected if they depend directly on each other. Syntactic connections usually happen within a sentence. Gathering all those connection across several…
To avoid detection, adversaries often use command-line obfuscation. There are numerous techniques of the command-line obfuscation, all designed to alter the command-line syntax without affecting its original functionality. This variability…
The synchronous reactive data flow language LUSTRE is an expressive language, equipped with a suite of tools for modelling, simulating and model-checking a wide variety of safety-critical systems. A critical intermediate step in the…
Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance degradation. This vulnerability primarily stems from the…
We introduce a flexible class of well-quasi-orderings (WQOs) on words that generalizes the ordering of (not necessarily contiguous) subwords. Each such WQO induces a class of piecewise testable languages (PTLs) as Boolean combinations of…
Large Language Models (LLMs) are now commonplace in conversation applications. However, their risks of misuse for generating harmful responses have raised serious societal concerns and spurred recent research on LLM conversation safety.…
Policies are designed to distinguish between correct and incorrect actions; they are types. But badly typed actions may cause not compile errors, but financial and reputational harm We demonstrate how even the most complex ABAC policies can…
Large Language Models (LLMs) such as ChatGPT and its competitors have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. This survey provides a comprehensive overview of…
Global types are formal specifications that describe communication protocols in terms of their global interactions. We present a new, streamlined language of global types equipped with a trace-based semantics and whose features and…
Mobile agents represent a new model for network computing. Many different languages have been used to implement mobile agents. The characteristics that make a language useful for writing mobile agents are: (1) their support of agent…
Artificial intelligence assisted mathematical proof has become a highly focused area nowadays. One key problem in this field is to generate formal mathematical proofs from natural language proofs. Due to historical reasons, the formal proof…
Population protocols are a model of distributed computation intended for the study of networks of independent computing agents with dynamic communication structure. Each agent has a finite number of states, and communication opportunities…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…
The "Ping-Pong" (PP) protocol is a two-way quantum key protocol based on entanglement. In this protocol, Bob prepares one maximally entangled pair of qubits, and sends one qubit to Alice. Then, Alice performs some necessary operations on…
Language change is a cultural evolutionary process in which variants of linguistic variables change in frequency through processes analogous to mutation, selection and genetic drift. In this work, we apply a recently-introduced method to…
Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…
A novel communication protocol based on an entangled pair of qubits is presented, allowing secure direct communication from one party to another without the need for a shared secret key. Since the information is transferred in a…