Skip to content
← Back to explorer

TFL: Targeted Bit-Flip Attack on Large Language Model

Jingkai Guo, Chaitali Chakrabarti, Deliang Fan · Feb 19, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Feb 19, 2026, 8:59 PM

Stale

Extraction refreshed

Apr 13, 2026, 6:43 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.25

Abstract

Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs), which exploit computer main memory (i.e., DRAM) vulnerabilities to flip a small number of bits in model weights, can severely disrupt LLM behavior. However, existing BFA on LLM largely induce un-targeted failure or general performance degradation, offering limited control over manipulating specific or targeted outputs. In this paper, we present TFL, a novel targeted bit-flip attack framework that enables precise manipulation of LLM outputs for selected prompts while maintaining almost no or minor degradation on unrelated inputs. Within our TFL framework, we propose a novel keyword-focused attack loss to promote attacker-specified target tokens in generative outputs, together with an auxiliary utility score that balances attack effectiveness against collateral performance impact on benign data. We evaluate TFL on multiple LLMs (Qwen, DeepSeek, Llama) and benchmarks (DROP, GSM8K, and TriviaQA). The experiments show that TFL achieves successful targeted LLM output manipulations with less than 50 bit flips and significantly reduced effect on unrelated queries compared to prior BFA approaches. This demonstrates the effectiveness of TFL and positions it as a new class of stealthy and targeted LLM model attack.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.25 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.

Benchmarks / Datasets

partial

GSM8K, TriviaQA, DROP

Confidence: Low Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: We evaluate TFL on multiple LLMs (Qwen, DeepSeek, Llama) and benchmarks (DROP, GSM8K, and TriviaQA).

Reported Metrics

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No metric anchors detected.

Evidence snippet: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Math
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.25
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

GSM8KTriviaQADROP

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

In this paper, we present TFL, a novel targeted bit-flip attack framework that enables precise manipulation of LLM outputs for selected prompts while maintaining almost no or minor degradation on unrelated inputs. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:43 AM · Grounded in abstract + metadata only

Key Takeaways

  • In this paper, we present TFL, a novel targeted bit-flip attack framework that enables precise manipulation of LLM outputs for selected prompts while maintaining almost no or minor…
  • Within our TFL framework, we propose a novel keyword-focused attack loss to promote attacker-specified target tokens in generative outputs, together with an auxiliary utility score…
  • Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: GSM8K, TriviaQA, DROP.
  • Verify metric definitions before comparing against your eval pipeline.

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • In this paper, we present TFL, a novel targeted bit-flip attack framework that enables precise manipulation of LLM outputs for selected prompts while maintaining almost no or minor degradation on unrelated inputs.
  • Within our TFL framework, we propose a novel keyword-focused attack loss to promote attacker-specified target tokens in generative outputs, together with an auxiliary utility score that balances attack effectiveness against collateral…
  • We evaluate TFL on multiple LLMs (Qwen, DeepSeek, Llama) and benchmarks (DROP, GSM8K, and TriviaQA).

Why It Matters For Eval

  • Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks.
  • We evaluate TFL on multiple LLMs (Qwen, DeepSeek, Llama) and benchmarks (DROP, GSM8K, and TriviaQA).

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: GSM8K, TriviaQA, DROP

  • Gap: Metric reporting is present

    No metric terms extracted.

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote