Pith. sign in

REVIEW 3 cited by

Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks

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 2310.10077 v1 pith:QZ6YBEA2 submitted 2023-10-16 cs.CL

classification cs.CL
keywords harmfulinstructionscontentdatasetsintentionsllmsattackscompositional
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and ethics. Unfortunately, they remain the risk of generating harmful content like hate speech and criminal activities in practical applications. Current approaches primarily rely on detecting, collecting, and training against harmful prompts to prevent such risks. However, they typically focused on the "superficial" harmful prompts with a solitary intent, ignoring composite attack instructions with multiple intentions that can easily elicit harmful content in real-world scenarios. In this paper, we introduce an innovative technique for obfuscating harmful instructions: Compositional Instruction Attacks (CIA), which refers to attacking by combination and encapsulation of multiple instructions. CIA hides harmful prompts within instructions of harmless intentions, making it impossible for the model to identify underlying malicious intentions. Furthermore, we implement two transformation methods, known as T-CIA and W-CIA, to automatically disguise harmful instructions as talking or writing tasks, making them appear harmless to LLMs. We evaluated CIA on GPT-4, ChatGPT, and ChatGLM2 with two safety assessment datasets and two harmful prompt datasets. It achieves an attack success rate of 95%+ on safety assessment datasets, and 83%+ for GPT-4, 91%+ for ChatGPT (gpt-3.5-turbo backed) and ChatGLM2-6B on harmful prompt datasets. Our approach reveals the vulnerability of LLMs to such compositional instruction attacks that harbor underlying harmful intentions, contributing significantly to LLM security development. Warning: this paper may contain offensive or upsetting content!

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  2. JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation

    cs.CR 2025-02 conditional novelty 6.0 of 10

    JBShield detects jailbreaks by checking whether a prompt activates both a toxic concept and a jailbreak concept inside an LLM, then steers those concepts to produce a safe refusal.

  3. Lightweight Safety Classification Using Pruned Language Models

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Intermediate-layer features of small LLMs plus a penalized logistic regression classifier achieve high F1 scores on content safety and prompt injection classification with very few labeled examples, per the paper's ex...

Pith tools