Tao Zhang

AI-driven algorithmic systems are increasingly adopted across various sectors, yet the lack of transparency can raise accountability concerns about claimed privacy protection measures. While machine-based audits offer one avenue for addressing these issues, they are often costly and time-consuming. Herd audit, on the other hand, offers a promising alternative by leveraging collective intelligence from end-users. However, the presence of epistemic disparity among auditors, resulting in varying levels of domain expertise and access to relevant knowledge, captured by the rational inattention model, may impact audit assurance. An effective herd audit must establish a credible accountability threat for algorithm developers, incentivizing them not to breach user trust. In this work, our objective is to develop a systematic framework that explores the impact of herd audits on algorithm developers through the lens of the Stackelberg game. Our analysis reveals the importance of easy access to information and the appropriate design of rewards, as they increase the auditors’ assurance in the audit process. In this context, herd audit serves as a deterrent to negligent behavior. Therefore, by enhancing herd accountability, herd audit contributes to responsible algorithm development, fostering trust between users and algorithms.

In dynamic mechanism design literature, one critical aspect has been typically ignored-the agents' periodic participation, which they can adapt and plan strategically. We propose a framework for dynamic principal-multiagent problems, augmenting the classic model by incorporating agents' periodic coupled decisions on participation and regular action selections. The principal faces adverse selection and designs a mechanism comprising a task policy profile (defining evolving agent action menus), a coupling policy profile (affecting agent utilities), and an off-switch function profile (assigning rewards or penalties upon agent withdrawal). Firstly, we introduce payoff-flow conservation-a sufficient condition to ensure dynamic incentive compatibility for regular actions. Secondly, we formulate a unique process, persistence transformation, which integrates task policy's implicit functions, enabling a closed-form off-switch function derivation, hence securing sufficient conditions for agents' coupled decisions' incentive compatibility, aligning with the principal's preferences. Thirdly, we go beyond the traditional envelope theorem by presenting a necessary condition for incentive compatibility, leveraging the coupled optimality of principal-desired actions. This approach helps explicitly formulate both the coupling and off-switch functions. Finally, we establish envelope-like conditions exclusively on the task policies, facilitating the application of the first-order approach.

This work studies a dynamic mechanism design problem in which a principal delegates decision makings to a group of privately-informed agents without the monetary transfer or burning. We consider that the principal privately possesses complete knowledge about the state transitions and study how she can use her private observation to support the incentive compatibility of the delegation via informational burning, a process we refer to as the looking-forward persuasion. The delegation mechanism is formulated in which the agents form belief hierarchies due to the persuasion and play a dynamic Bayesian game. We propose a novel randomized mechanism, known as Bayesian promised delegation (BPD), in which the periodic incentive compatibility is guaranteed by persuasions and promises of future delegations. We show that the BPD can achieve the same optimal social welfare as the original mechanism in stationary Markov perfect Bayesian equilibria. A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

Privacy is an essential issue in data trading markets. This work uses a mechanism design approach to study the optimal market model to economize the value of privacy of personal data, using differential privacy. The buyer uses a finite number of randomized algorithms to get access to the owners' data in a sequential-composition manner, in which each randomized algorithm is differentially private. Each usage of a randomized algorithm is referred to as a period. Due to the composability of differential privacy, there are inevitable privacy losses accumulated over periods. Hence, we allow the owners to leave the market at the end of any period by making stopping decisions. We define an instrumental kernel function to capture the instrumentalness of owners' preferences and model the formation of each owner's (both intrinsic and instrumental) preference over periods by taking into consideration the composability of differential privacy and the time-varying nature of privacy concerns. Our desideratum is to study the buyer's design regime of optimal market models in a dynamic environment when each owner makes coupled decisions of stopping and reporting of their preferences. The buyer seeks to design a privacy allocation rule that dynamically specifies the degree of privacy protections and a payment rule to compensate for the privacy losses of the owners. The buyer additionally chooses a payment rule which is independent of owners' reports of their preferences to influence the owners' stopping decisions. We characterize the dynamic incentive compatibility and provide a design principle to construct the payment rules in terms of the privacy allocation rule. Further, we relax the buyer's market design problem and provide a sufficient condition for an approximated dynamic incentive-compatible market model.

This work considers a novel information design problem and studies how the craft of payoff-relevant environmental signals solely can influence the behaviors of intelligent agents. The agents' strategic interactions are captured by a Markov game, in which each agent first selects one external signal from multiple signal sources as additional payoff-relevant information and then takes an action. There is a rational information designer (principal) who possesses one signal source and aims to influence the equilibrium behaviors of the agents by designing the information structure of her signals sent to the agents. We propose a direct information design approach that incentivizes each agent to select the signal sent by the principal, such that the design process avoids the predictions of the agents' strategic selection behaviors. We then introduce the design protocol given a goal of the designer which we refer to as obedient implementability (OIL) and characterize the OIL in a class of obedient sequential Markov perfect equilibria (O-SMPE). A design regime is proposed based on an approach which we refer to as the fixed-point alignment that incentivizes the agents to choose the signal sent by the principal, guarantees that the agents' policy profile of taking actions is the policy component of an O-SMPE and the principal's goal is achieved. We then formulate the principal's optimal goal selection problem in terms of information design and characterize the optimization problem by minimizing the fixed-point misalignments. The proposed approach can be applied to elicit desired behaviors of multi-agent systems in competing as well as cooperating settings and be extended to heterogeneous stochastic games in the complete- and the incomplete-information environments.

Vehicular ad hoc network (VANET) is an enabling technology in modern transportation systems for providing safety and valuable information, and yet vulnerable to a number of attacks from passive eavesdropping to active interfering. Intrusion detection systems (IDSs) are important devices that can mitigate the threats by detecting malicious behaviors. Furthermore, the collaborations among vehicles in VANETs can improve the detection accuracy by communicating their experiences between nodes. To this end, distributed machine learning is a suitable framework for the design of scalable and implementable collaborative detection algorithms over VANETs. One fundamental barrier to collaborative learning is the privacy concern as nodes exchange data among them. A malicious node can obtain sensitive information of other nodes by inferring from the observed data. In this paper, we propose a privacy-preserving machine-learning based collaborative IDS (PML-CIDS) for VANETs. The proposed algorithm employs the alternating direction method of multipliers (ADMM) to a class of empirical risk minimization (ERM) problems and trains a classifier to detect the intrusions in the VANETs. We use the differential privacy to capture the privacy notation of the PML-CIDS and propose a method of dual variable perturbation to provide dynamic differential privacy. We analyze theoretical performance and characterize the fundamental tradeoff between the security and privacy of the PML-CIDS. We also conduct numerical experiments using the NSL-KDD dataset to corroborate the results on the detection accuracy, security-privacy tradeoffs, and design.