Adversarial training is one of the most effective adversarial defenses, but it incurs a high computational cost. In this study, we show that transformers adversarially pretrained on diverse tasks can serve as robust foundation models and eliminate the need for adversarial training in downstream tasks. Specifically, we theoretically demonstrate that through in-context learning, a single adversarially pretrained transformer can robustly generalize to multiple unseen tasks without any additional training, i.e., without any parameter updates. This robustness stems from the model's focus on robust features and its resistance to attacks that exploit non-predictive features. Besides these positive findings, we also identify several limitations. Under certain conditions (though unrealistic), no universally robust single-layer transformers exist. Moreover, robust transformers exhibit an accuracy--robustness trade-off and require a large number of in-context demonstrations. The code is available at https://github.com/s-kumano/universally-robust-in-context-learner.

Reasoning about the causes behind observations is crucial to the formalization of rationality. While extensive research has been conducted on root cause analysis, most studies have predominantly focused on deterministic settings. In this paper, we investigate causation in more realistic nondeterministic domains, where the agent does not have any control on and may not know the choices that are made by the environment. We build on recent preliminary work on actual causation in the nondeterministic situation calculus to formalize more sophisticated forms of reasoning about actual causes in such domains. We investigate the notions of ``Certainly Causes'' and ``Possibly Causes'' that enable the representation of actual cause for agent actions in these domains. We then show how regression in the situation calculus can be extended to reason about such notions of actual causes.

A framework with sets of attacking arguments(SETAF) is an extension of the well-known Dung's Abstract Argumentation Frameworks (AAF s) that allows joint attacks on arguments. In this paper, we provide a translation from Normal Logic Programs (NLPs) to SETAFs and vice versa, from SETAFs to NLPs. We show that there is pairwise equivalence between their semantics, including the equivalence between L-stable and semi-stable semantics. Furthermore, for a class of NLPs called Redundancy-Free Atomic Logic Programs (RFALPs), there is also a structural equivalence as these back-and-forth translations are each other's inverse. Then, we show that RFALPs are as expressive as NLPs by transforming any NLP into an equivalent RFALP through a series of program transformations already known in the literature. We also show that these program transformations are confluent, meaning that every NLP will be transformed into a unique RFALP. The results presented in this paper enhance our understanding that NLPs and SETAFs are essentially the same formalism.

Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs, it has been empirically proved that malicious attackers could easily corrupt the fairness level of their predictions by adding perturbations to the input graph data. In this paper, we take crucial steps to study a novel problem of certifiable defense on the fairness level of GNNs. Specifically, we propose a principled framework named ELEGANT and present a detailed theoretical certification analysis for the fairness of GNNs. ELEGANT takes any GNNs as its backbone, and the fairness level of such a backbone is theoretically impossible to be corrupted under certain perturbation budgets for attackers. Notably, ELEGANT does not have any assumption over the GNN structure or parameters, and does not require re-training the GNNs to realize certification. Hence it can serve as a plug-and-play framework for any optimized GNNs ready to be deployed. We verify the satisfactory effectiveness of ELEGANT in practice through extensive experiments on real-world datasets across different backbones of GNNs, where ELEGANT is also demonstrated to be beneficial for GNN debiasing. Graph Neural Networks (GNNs) have emerged to be one of the most popular models to handle learning tasks on graphs (Kipf & Welling, 2017; Veličković et al., 2018) and made remarkable achievements in various domains (Feng et al., 2022; Li et al., 2022; Jin et al., 2023). Nevertheless, as GNNs are increasingly deployed in real-world decision-making scenarios, there has been an increasing societal concern on the fairness of GNN predictions. A primary reason is that most traditional GNNs do not consider fairness, and thus could exhibit bias against certain demographic subgroups. Here the demographic subgroups are usually divided by certain sensitive attributes, such as gender and race. To prevent GNNs from exhibiting biased predictions, multiple recent studies proposed fairness-aware GNNs (Agarwal et al., 2021; Dai & Wang, 2021; Li et al., 2021; Kang et al., 2022a; Ju et al., 2023) such that potential bias could be mitigated.

This paper is a contribution to the research on dynamics in assumption-based argumentation (ABA). We investigate situations where a given knowledge base undergoes certain changes. We show that two frequently investigated problems, namely enforcement of a given target atom and deciding strong equivalence of two given ABA frameworks, are intractable in general. Notably, these problems are both tractable for abstract argumentation frameworks (AFs) which admit a close correspondence to ABA by constructing semanticspreserving instances. Inspired by this observation, we search for tractable fragments for ABA frameworks by means of the instantiated AFs. We argue that the usual instantiation procedure is not suitable for the investigation of dynamic scenarios since too much information is lost when constructing the abstract framework. We thus consider an extension of AFs, called cvAFs, equipping arguments with conclusions and vulnerabilities in order to better anticipate their role after the underlying knowledge base is extended. We investigate enforcement and strong equivalence for cvAFs and present syntactic conditions to decide them. We show that the correspondence between cvAFs and ABA frameworks is close enough to capture dynamics in ABA. This yields the desired tractable fragment. We furthermore discuss consequences for the corresponding problems for logic programs.