Social-Engineering

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

Source DOI

Sub-category

Risk Domain

4Malicious Actors & Misuse

4.3Fraud, scams, and targeted manipulation

Using AI systems to gain a personal advantage over others such as through cheating, fraud, scams, blackmail or targeted manipulation of beliefs or behavior. Examples include AI-facilitated plagiarism for research or education, impersonating a trusted or fake individual for illegitimate financial benefit, or creating humiliating or sexual imagery.

psychologically manipulating victims into performing the desired actions for malicious purposes(p. 20)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (2)

Social-engineering attacks include phishing [294, 295], spams/bots [296, 297], impersonating [298, 299] (including deepfake [299]), fake online content [51, 300, 301, 302], and social network manipulation [303, 304, 305] et(p. 20)

Almost all types of social-engineering attacks can be enhanced by leveraging LLMs, especially in contextualizing deceptive messages to users. For example, recently people have also shown the possibility of using an LLM to impersonate a person’s style of conversation [298](p. 20)

Part of Resistance to Misuse