The 20 questions game to distinguish large language models

In a parallel with the 20 questions game, we present a method to determine whether two large language models (LLMs), placed in a black-box context, are the same or not. The goal is to use a small set of (benign) binary questions, typically under 20. We formalize the problem and first establish a baseline using a random selection of questions from known benchmark datasets, achieving an accuracy of nearly 100% within 20 questions. After showing optimal bounds for this problem, we introduce two effective questioning heuristics able to discriminate 22 LLMs by using half as many questions for the same task. These methods offer significant advantages in terms of stealth and are thus of interest to auditors or copyright owners facing suspicions of model leaks.

LLMs hallucinate graphs too: a structural perspective

It is known that LLMs do hallucinate, that is, they return incorrect information as facts. In this paper, we introduce the possibility to study these hallucinations under a structured form: graphs. Hallucinations in this context are incorrect outputs when prompted for well known graphs from the literature (e.g. Karate club, Les Mis\'erables, graph atlas). These hallucinated graphs have the advantage of being much richer than the factual accuracy -- or not -- of a fact; this paper thus argues that such rich hallucinations can be used to characterize the outputs of LLMs. Our first contribution observes the diversity of topological hallucinations from major modern LLMs. Our second contribution is the proposal of a metric for the amplitude of such hallucinations: the Graph Atlas Distance, that is the average graph edit distance from several graphs in the graph atlas set. We compare this metric to the Hallucination Leaderboard, a hallucination rank that leverages 10,000 times more prompts to obtain its ranking.

Under manipulations, are some AI models harder to audit?

Auditors need robust methods to assess the compliance of web platforms with the law. However, since they hardly ever have access to the algorithm, implementation, or training data used by a platform, the problem is harder than a simple metric estimation. Within the recent framework of manipulation-proof auditing, we study in this paper the feasibility of robust audits in realistic settings, in which models exhibit large capacities. We first prove a constraining result: if a web platform uses models that may fit any data, no audit strategy -- whether active or not -- can outperform random sampling when estimating properties such as demographic parity. To better understand the conditions under which state-of-the-art auditing techniques may remain competitive, we then relate the manipulability of audits to the capacity of the targeted models, using the Rademacher complexity. We empirically validate these results on popular models of increasing capacities, thus confirming experimentally that large-capacity models, which are commonly used in practice, are particularly hard to audit robustly. These results refine the limits of the auditing problem, and open up enticing questions on the connection between model capacity and the ability of platforms to manipulate audit attempts.

Fairness Auditing with Multi-Agent Collaboration

Existing work in fairness audits assumes that agents operate independently. In this paper, we consider the case of multiple agents auditing the same platform for different tasks. Agents have two levers: their collaboration strategy, with or without coordination beforehand, and their sampling method. We theoretically study their interplay when agents operate independently or collaborate. We prove that, surprisingly, coordination can sometimes be detrimental to audit accuracy, whereas uncoordinated collaboration generally yields good results. Experimentation on real-world datasets confirms this observation, as the audit accuracy of uncoordinated collaboration matches that of collaborative optimal sampling.

On the relevance of APIs facing fairwashed audits

Recent legislation required AI platforms to provide APIs for regulators to assess their compliance with the law. Research has nevertheless shown that platforms can manipulate their API answers through fairwashing. Facing this threat for reliable auditing, this paper studies the benefits of the joint use of platform scraping and of APIs. In this setup, we elaborate on the use of scraping to detect manipulated answers: since fairwashing only manipulates API answers, exploiting scraps may reveal a manipulation. To abstract the wide range of specific API-scrap situations, we introduce a notion of proxy that captures the consistency an auditor might expect between both data sources. If the regulator has a good proxy of the consistency, then she can easily detect manipulation and even bypass the API to conduct her audit. On the other hand, without a good proxy, relying on the API is necessary, and the auditor cannot defend against fairwashing. We then simulate practical scenarios in which the auditor may mostly rely on the API to conveniently conduct the audit task, while maintaining her chances to detect a potential manipulation. To highlight the tension between the audit task and the API fairwashing detection task, we identify Pareto-optimal strategies in a practical audit scenario. We believe this research sets the stage for reliable audits in practical and manipulation-prone setups.

FBI: Fingerprinting models with Benign Inputs

Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked for. While efficient in such a scenario, this nevertheless results in a lack of guarantee after a mere modification (like retraining, quantization) of a model. This paper tackles the challenges to propose i) fingerprinting schemes that are resilient to significant modifications of the models, by generalizing to the notion of model families and their variants, ii) an extension of the fingerprinting task encompassing scenarios where one wants to fingerprint not only a precise model (previously referred to as a detection task) but also to identify which model family is in the black-box (identification task). We achieve both goals by demonstrating that benign inputs, that are unmodified images, for instance, are sufficient material for both tasks. We leverage an information-theoretic scheme for the identification task. We devise a greedy discrimination algorithm for the detection task. Both approaches are experimentally validated over an unprecedented set of more than 1,000 networks.

Randomized Smoothing under Attack: How Good is it in Pratice?

Randomized smoothing is a recent and celebrated solution to certify the robustness of any classifier. While it indeed provides a theoretical robustness against adversarial attacks, the dimensionality of current classifiers necessarily imposes Monte Carlo approaches for its application in practice. This paper questions the effectiveness of randomized smoothing as a defense, against state of the art black-box attacks. This is a novel perspective, as previous research works considered the certification as an unquestionable guarantee. We first formally highlight the mismatch between a theoretical certification and the practice of attacks on classifiers. We then perform attacks on randomized smoothing as a defense. Our main observation is that there is a major mismatch in the settings of the RS for obtaining high certified robustness or when defeating black box attacks while preserving the classifier accuracy.

Algorithmic audits of algorithms, and the law

Algorithmic decision making is now widespread, ranging from health care allocation to more common actions such as recommendation or information ranking. The aim to audit these algorithms has grown alongside. In this paper, we focus on external audits that are conducted by interacting with the user side of the target algorithm, hence considered as a black box. Yet, the legal framework in which these audits take place is mostly ambiguous to researchers developing them: on the one hand, the legal value of the audit outcome is uncertain; on the other hand the auditors' rights and obligations are unclear. The contribution of this paper is to articulate two canonical audit forms to law, to shed light on these aspects: 1) the first audit form (we coin the Bobby audit form) checks a predicate against the algorithm, while the second (Sherlock) is more loose and opens up to multiple investigations. We find that: Bobby audits are more amenable to prosecution, yet are delicate as operating on real user data. This can lead to reject by a court (notion of admissibility). Sherlock audits craft data for their operation, most notably to build surrogates of the audited algorithm. It is mostly used for acts for whistleblowing, as even if accepted as a proof, the evidential value will be low in practice. 2) these two forms require the prior respect of a proper right to audit, granted by law or by the platform being audited; otherwise the auditor will be also prone to prosecutions regardless of the audit outcome. This article thus highlights the relation of current audits with law, in order to structure the growing field of algorithm auditing.

RoBIC: A benchmark suite for assessing classifiers robustness

Many defenses have emerged with the development of adversarial attacks. Models must be objectively evaluated accordingly. This paper systematically tackles this concern by proposing a new parameter-free benchmark we coin RoBIC. RoBIC fairly evaluates the robustness of image classifiers using a new half-distortion measure. It gauges the robustness of the network against white and black box attacks, independently of its accuracy. RoBIC is faster than the other available benchmarks. We present the significant differences in the robustness of 16 recent models as assessed by RoBIC.

SurFree: a fast surrogate-free black-box attack

Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking decrease in the amount of queries a black box attack submits to the target classifier, in order to forge adversarials. This particularly concerns the black-box score-based setup, where the attacker has access to top predicted probabilites: the amount of queries went from to millions of to less than a thousand. This paper presents SurFree, a geometrical approach that achieves a similar drastic reduction in the amount of queries in the hardest setup: black box decision-based attacks (only the top-1 label is available). We first highlight that the most recent attacks in that setup, HSJA, QEBA and GeoDA all perform costly gradient surrogate estimations. SurFree proposes to bypass these, by instead focusing on careful trials along diverse directions, guided by precise indications of geometrical properties of the classifier decision boundaries. We motivate this geometric approach before performing a head-to-head comparison with previous attacks with the amount of queries as a first class citizen. We exhibit a faster distortion decay under low query amounts (few hundreds to a thousand), while remaining competitive at higher query budgets.