An evolutionary approach to deception in multi-agent systems

Abstract

Understanding issues of trust and deception are key to designing robust, reliable multi-agent systems. This paper builds on previous work which examined the use of auctions as a model for exploring the concept of deception in such systems. We have previously described two forms of deceptive behaviour which can occur in a simulated repeated English auction. The first of these types of deception involves sniping or late bidding, which not only allows an agent to conceal its true valuation for an item, but also potentially allows it to win an item for which it may not possess the highest valuation. The second deceptive strategy involves the placing of false bids which are designed to reduce an opponent's potential profit. In this work we examine the potential shortcomings of those two strategies and investigate whether or not their individual strengths can be combined to produce a successful hybrid deceptive strategy.

On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services

“…Novel Issues: As noted in Section 1, AI systems have demonstrated the ability to learn and independently develop unethical strategies (e.g. deception [90], aggression [76]). In the near future, it will be vital to assess AI's novel behavioral patterns from an ethical perspective.…”

“…These concerns are quite valid as numerous studies showed that AI is capable of exhibiting unethical behaviors. AI agents have been shown to produce biased outcomes [63,110] and even demonstrate the ability to independently develop deceptive tactics such as deception in experimental settings [29,90]. Although a large number of techniques have been developed in recent years, the practice of ethical AI techniques in finance is still in its nascent stages.…”