Pritha Gupta

Jiawen Wang, Pritha Gupta, Ivan Habernal et al.

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these attacks. This paper studies effective prompt injection attacks against the $\mathbf{14}$ most popular open-source LLMs on five attack benchmarks. Current metrics only consider successful attacks, whereas our proposed Attack Success Probability (ASP) also captures uncertainty in the model's response, reflecting ambiguity in attack feasibility. By comprehensively analyzing the effectiveness of prompt injection attacks, we propose a simple and effective hypnotism attack; results show that this attack causes aligned language models, including Stablelm2, Mistral, Openchat, and Vicuna, to generate objectionable behaviors, achieving around $90$% ASP. They also indicate that our ignore prefix attacks can break all $\mathbf{14}$ open-source LLMs, achieving over $60$% ASP on a multi-categorical dataset. We find that moderately well-known LLMs exhibit higher vulnerability to prompt injection attacks, highlighting the need to raise public awareness and prioritize efficient mitigation strategies.

Karlson Pfannschmidt, Pritha Gupta, Björn Haddenhorst et al.

Choice functions accept a set of alternatives as input and produce a preferred subset of these alternatives as output. We study the problem of learning such functions under conditions of context-dependence of preferences, which means that the preference in favor of a certain choice alternative may depend on what other options are also available. In spite of its practical relevance, this kind of context-dependence has received little attention in preference learning so far. We propose a suitable model based on context-dependent (latent) utility functions, thereby reducing the problem to the task of learning such utility functions. Practically, this comes with a number of challenges. For example, the set of alternatives provided as input to a choice function can be of any size, and the output of the function should not depend on the order in which the alternatives are presented. To meet these requirements, we propose two general approaches based on two representations of context-dependent utility functions, as well as instantiations in the form of appropriate end-to-end trainable neural network architectures. Moreover, to demonstrate the performance of both networks, we present extensive empirical evaluations on both synthetic and real-world datasets.

Karlson Pfannschmidt, Pritha Gupta, Eyke Hüllermeier

Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. Current approaches commonly focus on ranking by scoring, i.e., on learning an underlying latent utility function that seeks to capture the inherent utility of each object. These approaches, however, are not able to take possible effects of context-dependence into account, where context-dependence means that the utility or usefulness of an object may also depend on what other objects are available as alternatives. In this paper, we formalize the problem of context-dependent ranking and present two general approaches based on two natural representations of context-dependent ranking functions. Both approaches are instantiated by means of appropriate neural network architectures, which are evaluated on suitable benchmark task.