Related papers: On Backdoors To Tractable Constraint Languages
Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL) fine-tuning, a new paradigm that allows language models to…
We study constraint satisfaction problems (CSPs) where the constraint languages are defined by finite automata, giving rise to automata-based CSPs. The key notion is the concept of Automatic Constraint Satisfaction Problem ($AutCSP$), where…
In pursuit of a deeper understanding of Boolean Promise Constraint Satisfaction Problems (PCSPs), we identify a class of problems with restricted structural complexity, which could serve as a promising candidate for complete…
A natural strengthening of an algorithm for the (promise) constraint satisfaction problem is its singleton version: we first fix a variable to an element from its domain, then run the algorithm, and remove the element from the domain if the…
Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when…
Over the last two decades, propositional satisfiability (SAT) has become one of the most successful and widely applied techniques for the solution of NP-complete problems. The aim of this paper is to investigate theoretically how Sat can be…
Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. One commonly used method to assess the reliability of LLMs' responses is uncertainty estimation, which gauges…
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however, are effective only for specific pre-defined downstream…
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…
A set $S$ of vertices of a graph is a defensive alliance if, for each element of $S$, the majority of its neighbours is in $S$. We consider the notion of local minimality in this paper. We are interested in locally minimal defensive…
Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…
Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…
The usefulness of parameterized algorithmics has often depended on what Niedermeier has called, "the art of problem parameterization". In this paper we introduce and explore a novel but general form of parameterization: the number of…
Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…
We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differently on a particular input known as the "trigger", while…
Grammar-based compression is a popular and powerful approach to compressing repetitive texts but until recently its relatively poor time-space trade-offs during real-life construction made it impractical for truly massive datasets such as…
The classifications of temporal and phylogeny constraint languages stand among the most seminal complexity classifications within infinite-domain Constraint Satisfaction Problems (CSPs), yet remain the most mysterious in terms of algorithms…
A class of valued constraint satisfaction problems (VCSPs) is characterised by a valued constraint language, a fixed set of cost functions on a finite domain. An instance of the problem is specified by a sum of cost functions from the…
The Promise Constraint Satisfaction Problem (PCSP for short) is a generalization of the well-studied Constraint Satisfaction Problem (CSP). The PCSP has its roots in such classic problems as the Approximate Graph Coloring and the…