This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Technical mechanisms operating on non-model components of the AI system without modifying model weights. Components include: input/output interfaces, runtime environment, guardrail/monitoring classifiers, tool chain, and hardware.
Also in AI System
To counter the extraction attacks, the earlier defense strategies [289]–[291] against model extraction attacks usually modify or restrict the generated response provided for each query. In specific, the defender usually deploys a disruption-based strategy [290] to adjust the numerical precision of model loss, add noise to the output, or return random responses. However, this type of method usually introduces a performance-cost tradeoff [290], [292]–[294]. Besides, recent work [137] has been demonstrated to circumvent the disruption-based defenses via disruption detection and recovery. Therefore, some attempts adopt warning-based methods [295] or watermarking methods [296] [297] to defend against the extraction attacks. Specifically, warning-based methods are proposed to measure the distance between continuous queries to identify the malware requests, while watermarking methods are used to claim the ownership of the stolen models.
Reasoning
Defenses span output modification, query pattern monitoring, and watermarking—multiple non-model technical approaches.
Mitigation in Input Modules
Mitigating the threat posed by the input module presents a significant challenge for LLM developers due to the diversity of the harmful inputs and adversarial prompts [209], [210].
1.2.1 Guardrails & FilteringMitigation in Input Modules > Defensive Prompt Design
Directly modifying the input prompts is a viable approach to steer the behavior of the model and foster the generation of responsible outputs. This method integrates contextual information or constraints in the prompts to provide background knowledge and guidelines while generating the output [22].
1.2.1 Guardrails & FilteringMitigation in Input Modules > Malicious Prompt Detection
Different from the methods of designing defensive prompts to preprocess the input, the malicious prompt detection method aims to detect and filter out the harmful prompts through the input safeguard
1.2.1 Guardrails & FilteringMitigation in Language Models
This section delves into mitigating risks associated with models, encompassing privacy preservation, detoxification and debiasing, mitigation of hallucinations, and defenses against model attacks.
1.1 ModelMitigation in Language Models > Privacy Preserving
Privacy leakage is a crucial risk of LLMs, since the powerful memorization and association capabilities of LLMs raise the risk of revealing private information within the training data. Researchers are devoted to designing privacypreserving frameworks in LLMs [226], [227], aiming to safeguard sensitive PII from possible disclosure during humanmachine conservation
1.1 ModelMitigation in Language Models > Detoxifying and Debiasing
To reduce the toxicity and bias of LLMs, prior efforts mainly focus on enhancing the quality of training data and conducting safety training.
1.1 ModelRisk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Cui, Tianyu; Wang, Yanling; Fu, Chuanpu; Xiao, Yong; Li, Sijia; Deng, Xinhao; Liu, Yunpeng; Zhang, Qinglin; Qiu, Ziyi; Li, Peiyang; Tan, Zhixing; Xiong, Junwu; Kong, Xinyu; Wen, Zujie; Xu, Ke; Li, Qi (2024)
Despite their impressive capabilities, large lan- guage models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon com- monly known as “hallucination”. In this work, we propose a simple Induce-then-Contrast De- coding (ICD) strategy to alleviate hallucina- tions. We first construct a factually weak LLM by inducing hallucinations from the original LLMs. Then, we penalize these induced hallu- cinations during decoding to enhance the fac- tuality of the generated content. Concretely, we determine the final next-token predictions by amplifying the predictions from the orig- inal model and downplaying the induced un- truthful predictions via contrastive decoding. Experimental results on both discrimination- based and generation-based hallucination eval- uation benchmarks, such as TruthfulQA and FACTSCORE, demonstrate that our proposed ICD methods can effectively enhance the factu- ality of LLMs across various model sizes and families. For example, when equipped with ICD, Llama2-7B-Chat and Mistral-7B-Instruct achieve performance comparable to ChatGPT and GPT4 on TruthfulQA, respectively.
Operate and Monitor
Running, maintaining, and monitoring the AI system post-deployment
Deployer
Entity that integrates and deploys the AI system for end users
Manage
Prioritising, responding to, and mitigating AI risks
