Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services. This innovation enhances the capabilities of LLMs, but it also introduces risks, as these plugins developed by various third parties cannot be easily trusted. This paper proposes a new attacking framework to examine security and safety vulnerabilities within LLM platforms that incorporate third-party services. Applying our framework specifically to widely used LLMs, we identify real-world malicious attacks across various domains on third-party APIs that can imperceptibly modify LLM outputs. The paper discusses the unique challenges posed by third-party API integration and offers strategic possibilities to improve the security and safety of LLM ecosystems moving forward. Our code is released at https://github.com/vk0812/Third-Party-Attacks-on-LLMs.

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Intervention by Semantic Smoothing (CISS), a novel framework towards robustness against natural language attacks. Instead of merely fitting observational data, CISS learns causal effects p(y|do(x)) by smoothing in the latent semantic space to make robust predictions, which scales to deep architectures and avoids tedious construction of noise customized for specific attacks. CISS is provably robust against word substitution attacks, as well as empirically robust even when perturbations are strengthened by unknown attack algorithms. For example, on YELP, CISS surpasses the runner-up by 6.7% in terms of certified robustness against word substitutions, and achieves 79.4% empirical robustness when syntactic attacks are integrated.

Grammatical Error Correction (GEC) systems perform a sequence-to-sequence task, where an input word sequence containing grammatical errors, is corrected for these errors by the GEC system to output a grammatically correct word sequence. With the advent of deep learning methods, automated GEC systems have become increasingly popular. For example, GEC systems are often used on speech transcriptions of English learners as a form of assessment and feedback - these powerful GEC systems can be used to automatically measure an aspect of a candidate's fluency. The count of \textit{edits} from a candidate's input sentence (or essay) to a GEC system's grammatically corrected output sentence is indicative of a candidate's language ability, where fewer edits suggest better fluency. The count of edits can thus be viewed as a \textit{fluency score} with zero implying perfect fluency. However, although deep learning based GEC systems are extremely powerful and accurate, they are susceptible to adversarial attacks: an adversary can introduce a small, specific change at the input of a system that causes a large, undesired change at the output. When considering the application of GEC systems to automated language assessment, the aim of an adversary could be to cheat by making a small change to a grammatically incorrect input sentence that conceals the errors from a GEC system, such that no edits are found and the candidate is unjustly awarded a perfect fluency score. This work examines a simple universal substitution adversarial attack that non-native speakers of English could realistically employ to deceive GEC systems used for assessment.

This work proposes a structured approach to baselining a model, identifying attack vectors, and securing the machine learning models after deployment. This method for securing each model post deployment is called the BAD (Build, Attack, and Defend) Architecture. Two implementations of the BAD architecture are evaluated to quantify the adversarial life cycle for a black box Sentiment Analysis system. As a challenging diagnostic, the Jigsaw Toxic Bias dataset is selected as the baseline in our performance tool. Each implementation of the architecture will build a baseline performance report, attack a common weakness, and defend the incoming attack. As an important note: each attack surface demonstrated in this work is detectable and preventable. The goal is to demonstrate a viable methodology for securing a machine learning model in a production setting.