Pith. sign in

REVIEW 9 cited by

Adversarial Demonstration Attacks on Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.14950 v2 pith:SHDFL7Z3 submitted 2023-05-24 cs.CL cs.AIcs.CRcs.LG

classification cs.CLcs.AIcs.CRcs.LG
keywords demonstrationsattackinputmodelsadversarialdemonstrationllmssecurity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the emergence of more powerful large language models (LLMs), such as ChatGPT and GPT-4, in-context learning (ICL) has gained significant prominence in leveraging these models for specific tasks by utilizing data-label pairs as precondition prompts. While incorporating demonstrations can greatly enhance the performance of LLMs across various tasks, it may introduce a new security concern: attackers can manipulate only the demonstrations without changing the input to perform an attack. In this paper, we investigate the security concern of ICL from an adversarial perspective, focusing on the impact of demonstrations. We propose a novel attack method named advICL, which aims to manipulate only the demonstration without changing the input to mislead the models. Our results demonstrate that as the number of demonstrations increases, the robustness of in-context learning would decrease. Additionally, we also identify the intrinsic property of the demonstrations is that they can be used (prepended) with different inputs. As a result, it introduces a more practical threat model in which an attacker can attack the test input example even without knowing and manipulating it. To achieve it, we propose the transferable version of advICL, named Transferable-advICL. Our experiment shows that the adversarial demonstration generated by Transferable-advICL can successfully attack the unseen test input examples. We hope that our study reveals the critical security risks associated with ICL and underscores the need for extensive research on the robustness of ICL, particularly given its increasing significance in the advancement of LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A First Look at the Security Issues in the Model Context Protocol Ecosystem

    cs.CR 2025-10 conditional novelty 8.0 of 10

    Analysis of 67,057 servers across six registries reveals widespread conditions for server hijacking and metadata manipulation in MCP, with a new tool MCPInspect flagging 833 vulnerable servers and 18 with suspicious d...

  2. When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Task-preserving perturbations of correct exemplars can degrade ICL performance by changing the effective evidence mixture used for inference.

  3. Visual Persuasion: What Influences Decisions of Vision-Language Models?

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Naturalistic edits to background, lighting, and staging systematically shift the choices of frontier vision-language models, and a new optimization-plus-interpretation framework (CVPO) discovers and explains the visua...

  4. SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

    cs.CR 2025-10 conditional novelty 6.0 of 10

    A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.

  5. Towards an AI co-scientist

    cs.AI 2025-02 unverdicted novelty 6.0 of 10

    A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.

  6. SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

    cs.LG 2023-10 accept novelty 6.0 of 10

    SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.

  7. From Text to DSL: Evaluating Grammar-Based Model Generation Using Open LLMs

    cs.SE 2026-05 unverdicted novelty 4.0 of 10

    Compact open-source LLMs can produce syntactically valid, semantically complete, and inter-model consistent DSL models from text via few-shot prompting, with some 7B-12B models matching much larger ones in quality.

  8. Jailbreak Attacks and Defenses Against Large Language Models: A Survey

    cs.CR 2024-07 accept novelty 4.0 of 10

    A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.

  9. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

    cs.CR 2025-02 unverdicted novelty 2.0 of 10

    A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.

Pith tools