Ghassan Karame
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ghassan Karame has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Giorgia Azzurra Marson
NEC Labs Europe Germany
3 shared publications Pascal Zimmer
Ruhr-Universtät Bochum
3 shared publications- Sebastien Andreina
NEC Laboratories Europe
2 shared publications Sébastien Andreina
NEC Labs Europe, Germany
2 shared publicationsDavid Paaßen
University of Duisburg-Essen
1 shared publication- Lorenzo Alluminio
NEC Labs Europe Heidelberg Germany
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (15) , 15382-15390
On the Robustness of Distributed Machine Learning Against Transfer Attacks
Although distributed machine learning (distributed ML) is gaining considerable attention in the community, prior works have independently looked at instances of distributed ML in either the training or the inference phase. No prior work has examined the combined robustness stemming from distributing both the learning and the inference process. In this work, we explore, for the first time, the robustness of distributed ML models that are fully heterogeneous in training data, architecture, scheduler, optimizer, and other model parameters. Supported by theory and extensive experimental validation using CIFAR10 and FashionMNIST, we show that such properly distributed ML instantiations achieve across-the-board improvements in accuracy-robustness tradeoffs against state-of-the-art transfer-based attacks that could otherwise not be realized by current ensemble or federated learning instantiations. For instance, our experiments on CIFAR10 show that for the Common Weakness attack, one of the most powerful state-of-the-art transfer-based attacks, our method improves robust accuracy by up to 40%, with a minimal impact on clean task accuracy.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (15) , 15382-15390
Open AccessOn the Robustness of Distributed Machine Learning Against Transfer Attacks
Although distributed machine learning (distributed ML) is gaining considerable attention in the community, prior works have independently looked at instances of distributed ML in either the training or the inference phase. No prior work has examined the combined robustness stemming from distributing both the learning and the inference process. In this work, we explore, for the first time, the robustness of distributed ML models that are fully heterogeneous in training data, architecture, scheduler, optimizer, and other model parameters. Supported by theory and extensive experimental validation using CIFAR10 and FashionMNIST, we show that such properly distributed ML instantiations achieve across-the-board improvements in accuracy-robustness tradeoffs against state-of-the-art transfer-based attacks that could otherwise not be realized by current ensemble or federated learning instantiations. For instance, our experiments on CIFAR10 show that for the Common Weakness attack, one of the most powerful state-of-the-art transfer-based attacks, our method improves robust accuracy by up to 40%, with a minimal impact on clean task accuracy.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (19) , 21859-21868
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (19) , 21859-21868
Open AccessClosing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.
- Open Access
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.
Open AccessClosing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.
- Open Access
EF/CF: High Performance Smart Contract Fuzzing for Exploit Generation
Smart contracts are increasingly being used to manage large numbers of high-value cryptocurrency accounts. There is a strong demand for automated, efficient, and comprehensive methods to detect security vulnerabilities in a given contract. While the literature features a plethora of analysis methods for smart contracts, the existing proposals do not address the increasing complexity of contracts. Existing analysis tools suffer from false alarms and missed bugs in today's smart contracts that are increasingly defined by complexity and interdependencies. To scale accurate analysis to modern smart contracts, we introduce EF/CF, a high-performance fuzzer for Ethereum smart contracts. In contrast to previous work, EF/CF efficiently and accurately models complex smart contract interactions, such as reentrancy and cross-contract interactions, at a very high fuzzing throughput rate. To achieve this, EF/CF transpiles smart contract bytecode into native C++ code, thereby enabling the reuse of existing, optimized fuzzing toolchains. Furthermore, EF/CF increases fuzzing efficiency by employing a structure-aware mutation engine for smart contract transaction sequences and using a contract's ABI to generate valid transaction inputs. In a comprehensive evaluation, we show that EF/CF scales better -- without compromising accuracy -- to complex contracts compared to state-of-the-art approaches, including other fuzzers, symbolic/concolic execution, and hybrid approaches. Moreover, we show that EF/CF can automatically generate transaction sequences that exploit reentrancy bugs to steal Ether.
Open AccessEF/CF: High Performance Smart Contract Fuzzing for Exploit Generation
Smart contracts are increasingly being used to manage large numbers of high-value cryptocurrency accounts. There is a strong demand for automated, efficient, and comprehensive methods to detect security vulnerabilities in a given contract. While the literature features a plethora of analysis methods for smart contracts, the existing proposals do not address the increasing complexity of contracts. Existing analysis tools suffer from false alarms and missed bugs in today's smart contracts that are increasingly defined by complexity and interdependencies. To scale accurate analysis to modern smart contracts, we introduce EF/CF, a high-performance fuzzer for Ethereum smart contracts. In contrast to previous work, EF/CF efficiently and accurately models complex smart contract interactions, such as reentrancy and cross-contract interactions, at a very high fuzzing throughput rate. To achieve this, EF/CF transpiles smart contract bytecode into native C++ code, thereby enabling the reuse of existing, optimized fuzzing toolchains. Furthermore, EF/CF increases fuzzing efficiency by employing a structure-aware mutation engine for smart contract transaction sequences and using a contract's ABI to generate valid transaction inputs. In a comprehensive evaluation, we show that EF/CF scales better -- without compromising accuracy -- to complex contracts compared to state-of-the-art approaches, including other fuzzers, symbolic/concolic execution, and hybrid approaches. Moreover, we show that EF/CF can automatically generate transaction sequences that exploit reentrancy bugs to steal Ether.
- Open Access
Estimating Patch Propagation Times across (Blockchain) Forks
The wide success of Bitcoin has led to a huge surge of alternative cryptocurrencies (altcoins). Most altcoins essentially fork Bitcoin's code with minor modifications, such as the number of coins to be minted, the block size, and the block generation time. As such, they are often deemed identical to Bitcoin in terms of security, robustness, and maturity. In this paper, we show that this common conception is misleading. By mining data retrieved from the GitHub repositories of various altcoin projects, we estimate the time it took to propagate relevant patches from Bitcoin to the altcoins. We find that, while the Bitcoin development community is quite active in fixing security flaws of Bitcoin's code base, forked cryptocurrencies are not as rigorous in patching the same vulnerabilities (inherited from Bitcoin). In some cases, we observe that even critical vulnerabilities, discovered and fixed within the Bitcoin community, have been addressed by the altcoins tens of months after disclosure. Besides raising awareness of this problem, our work aims to motivate the need for a proper responsible disclosure of vulnerabilities to all forked chains prior to reporting them publicly.
Open AccessEstimating Patch Propagation Times across (Blockchain) Forks
The wide success of Bitcoin has led to a huge surge of alternative cryptocurrencies (altcoins). Most altcoins essentially fork Bitcoin's code with minor modifications, such as the number of coins to be minted, the block size, and the block generation time. As such, they are often deemed identical to Bitcoin in terms of security, robustness, and maturity. In this paper, we show that this common conception is misleading. By mining data retrieved from the GitHub repositories of various altcoin projects, we estimate the time it took to propagate relevant patches from Bitcoin to the altcoins. We find that, while the Bitcoin development community is quite active in fixing security flaws of Bitcoin's code base, forked cryptocurrencies are not as rigorous in patching the same vulnerabilities (inherited from Bitcoin). In some cases, we observe that even critical vulnerabilities, discovered and fixed within the Bitcoin community, have been addressed by the altcoins tens of months after disclosure. Besides raising awareness of this problem, our work aims to motivate the need for a proper responsible disclosure of vulnerabilities to all forked chains prior to reporting them publicly.