Bitget App
Trade smarter
Buy cryptoMarketsTradeFuturesEarnWeb3SquareMore
Trade
Spot
Buy and sell crypto with ease
Margin
Amplify your capital and maximize fund efficiency
Onchain
Going Onchain, without going Onchain!
Convert
Zero fees, no slippage
Explore
Launchhub
Gain the edge early and start winning
Copy
Copy elite trader with one click
Bots
Simple, fast, and reliable AI trading bot
Trade
USDT-M Futures
Futures settled in USDT
USDC-M Futures
Futures settled in USDC
Coin-M Futures
Futures settled in cryptocurrencies
Explore
Futures guide
A beginner-to-advanced journey in futures trading
Futures promotions
Generous rewards await
Overview
A variety of products to grow your assets
Simple Earn
Deposit and withdraw anytime to earn flexible returns with zero risk
On-chain Earn
Earn profits daily without risking principal
Structured Earn
Robust financial innovation to navigate market swings
VIP and Wealth Management
Premium services for smart wealth management
Loans
Flexible borrowing with high fund security
I never expected that AI stole my wallet

I never expected that AI stole my wallet

ChaincatcherChaincatcher2024/11/22 06:22
By:OdailyNews

When the training data is contaminated, can we still trust AI?

Author: Azuma, Odaily Planet Daily

On November 22, Beijing time, Slow Fog founder Yu Xian posted a bizarre case on his personal X ------ a user's wallet was "hacked" by AI…

I never expected that AI stole my wallet image 0

The ins and outs of this case are as follows.

Early this morning, X user r_ocky.eth revealed that he had previously hoped to use ChatGPT to assist in creating a pump.fun trading bot.

rocky.eth provided ChatGPT with his requirements, and ChatGPT returned a piece of code that could indeed help rocky.eth deploy a bot that met his needs, but he never expected that the code would contain hidden phishing content ------ r_ocky.eth linked his main wallet and consequently lost $2,500.

I never expected that AI stole my wallet image 1

From the screenshot posted by r_ocky.eth, the code provided by ChatGPT sends the address private key to a phishing API website, which is the direct cause of the theft.

While rocky.eth fell into the trap, the attacker reacted extremely quickly, transferring all assets from rocky.eth's wallet to another address (FdiBGKS8noGHY2fppnDgcgCQts95Ww8HSLUvWbzv1NhX) within half an hour. Subsequently, r_ocky.eth traced on-chain and found an address suspected to belong to the attacker's main wallet (2jwP4cuugAAYiGMjVuqvwaRS2Axe6H6GvXv3PxMPQNeC).

I never expected that AI stole my wallet image 2

On-chain information shows that this address has currently accumulated over $100,000 in "stolen funds," leading r_ocky.eth to suspect that such attacks may not be isolated incidents, but rather part of a larger-scale attack event.

After the incident, r_ocky.eth expressed disappointment, stating that he has lost trust in OpenAI (the company that developed ChatGPT) and called for OpenAI to promptly address the abnormal phishing content.

So, why would ChatGPT, as the most popular AI application today, provide phishing content?

In this regard, Yu Xian characterized the fundamental cause of this incident as "AI poisoning attacks," pointing out that there are widespread deceptive behaviors in LLMs like ChatGPT and Claude.

The so-called "AI poisoning attack" refers to the act of deliberately corrupting AI training data or manipulating AI algorithms. The attackers could be insiders, such as disgruntled current or former employees, or external hackers, with motives that may include causing reputational and brand damage, altering the credibility of AI decision-making, or slowing down or sabotaging AI processes. Attackers can distort the model's learning process by embedding misleading labels or features in the data, leading to erroneous results during deployment and operation.

In light of this incident, the reason ChatGPT provided phishing code to r_ocky.eth is likely because the AI model was contaminated with materials containing phishing content during training, but the AI seemingly failed to recognize the phishing content hidden beneath the regular materials. After learning from it, the AI then provided this phishing content to the user, resulting in the occurrence of this incident.

With the rapid development and widespread adoption of AI, the threat of "poisoning attacks" has become increasingly significant. In this incident, although the absolute amount lost is not large, the extended implications of such risks are enough to raise alarms ------ assuming it occurred in other fields, such as AI-assisted driving…

I never expected that AI stole my wallet image 3

In response to a user's question, Yu Xian mentioned a potential measure to mitigate such risks, which is to have ChatGPT add some form of code review mechanism.

Victim r_ocky.eth also stated that he has contacted OpenAI regarding this matter. Although he has not yet received a response, he hopes that this case can serve as an opportunity for OpenAI to pay attention to such risks and propose potential solutions.

0

Disclaimer: The content of this article solely reflects the author's opinion and does not represent the platform in any capacity. This article is not intended to serve as a reference for making investment decisions.

PoolX: Earn new token airdrops
Lock your assets and earn 10%+ APR
Lock now!