REVIEW 6 cited by
Backdoor Attacks for In-Context Learning with 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
Backdoor Attacks for In-Context Learning with Language Models
read the original abstract
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor attacks, where an adversary tampers with a machine learning model in order to make it perform some malicious behavior on inputs that contain a predefined backdoor trigger. We show that the in-context learning ability of large language models significantly complicates the question of developing backdoor attacks, as a successful backdoor must work against various prompting strategies and should not affect the model's general purpose capabilities. We design a new attack for eliciting targeted misclassification when language models are prompted to perform a particular target task and demonstrate the feasibility of this attack by backdooring multiple large language models ranging in size from 1.3 billion to 6 billion parameters. Finally we study defenses to mitigate the potential harms of our attack: for example, while in the white-box setting we show that fine-tuning models for as few as 500 steps suffices to remove the backdoor behavior, in the black-box setting we are unable to develop a successful defense that relies on prompt engineering alone.
Forward citations
Cited by 6 Pith papers
-
A First Look at the Security Issues in the Model Context Protocol Ecosystem
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...
-
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
ASB is a new benchmark that tests 10 prompt injection attacks, memory poisoning, a novel Plan-of-Thought backdoor attack, and 11 defenses on LLM agents across 13 models, finding attack success rates up to 84.3% and li...
-
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
Adversarial fine-tuning evades activation-based steganography detection in five LLMs while preserving secret recovery, but a recontextualization dataset restores both ridge and MLP probe detectability.
-
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
BadStyle creates stealthy backdoors in LLMs by poisoning samples with imperceptible style triggers and using an auxiliary loss to stabilize payload injection, achieving high attack success rates across multiple models...
-
LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.
-
Public Data Assisted Differentially Private In-Context Learning
A private ICL algorithm that aggregates LLM responses with DPM clustering and uses public data representatives achieves near-non-private utility at epsilon=1.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.