REVIEW 7 cited by
BadEdit: Backdooring large language models by model editing
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
read the original abstract
Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues, for the first time, we formulate backdoor injection as a lightweight knowledge editing problem, and introduce the BadEdit attack framework. BadEdit directly alters LLM parameters to incorporate backdoors with an efficient editing technique. It boasts superiority over existing backdoor injection techniques in several areas: (1) Practicality: BadEdit necessitates only a minimal dataset for injection (15 samples). (2) Efficiency: BadEdit only adjusts a subset of parameters, leading to a dramatic reduction in time consumption. (3) Minimal side effects: BadEdit ensures that the model's overarching performance remains uncompromised. (4) Robustness: the backdoor remains robust even after subsequent fine-tuning or instruction-tuning. Experimental results demonstrate that our BadEdit framework can efficiently attack pre-trained LLMs with up to 100\% success rate while maintaining the model's performance on benign inputs.
Forward citations
Cited by 7 Pith papers
-
Triggering Stealthy Feature Map Backdoors via Physical Fault Injection in Embedded Neural Networks
Precise electromagnetic or voltage faults on ARM Cortex-M4 can trigger feature-map backdoors in quantized CNNs that remain dormant without the fault and evade input-space detectors.
-
FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents
FORGE poisons deep-research planning with coordinated fake reasoning documents, reaching 26.4% PRISM report contamination at five injections; Root Query Anchoring halves that severity.
-
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
A handful of weight-bit flips (as few as 12) can bias LLM outputs toward a target entity or stance, with limited effect on non-target tasks and output distributions.
-
(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
A runtime-extension Trojan turns a single poisoned sample into a 97%+ backdoor via replay/amplification and leaks training hyperparameters through watermarked weights or innocuous text codewords.
-
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
LETHE uses parameter-level model merging plus prompt-level word definitions to dilute backdoor behavior in LLMs, cutting attack success to below 7% in most tested settings.
-
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
A survey claims proactive defenses against LLM misinformation outperform post-hoc detection by up to 63%, but no meta-analysis details are provided to support the claim.
-
A Survey on Data Security in Large Language Models
A survey of data security risks in LLMs that organizes threats, defenses, and evaluation datasets, with notable factual errors in its tables.
Discussion (0). Continue with ORCID to comment.